A curated list of awesome online test-time adaptation resources. Your contributions are always welcome!
-
T3A[Iwasawa and Matsuo, Proc. NeurIPS 2021] Test-time classifier adjustment module for model-agnostic domain generalization [PDF] [G-Scholar] [CODE] -
PAD[Wu et al., Proc. NeurIPS Workshops 2021] Domain-agnostic test-time adaptation by prototypical training with auxiliary data [PDF] [G-Scholar] -
NOTE[Gong et al., Proc. NeurIPS 2022] NOTE: Robust continual test-time adaptation against temporal correlation [PDF] [G-Scholar] [CODE] -
CoTTA[Wang et al., Proc. CVPR 2022] Continual test-time domain adaptation [PDF] [G-Scholar] [CODE] -
SAR[Niu et al., Proc. ICLR 2023] Towards stable test-time adaptation in dynamic wild world [PDF] [G-Scholar] [CODE] -
FEDTHE+[Jiang and Lin, Proc. ICLR 2023] Test-time robust personalization for federated learning [PDF] [G-Scholar] [CODE] -
AdaNPC[Zhang et al., Proc. ICML 2023] AdaNPC: Exploring non-parametric classifier for test-time adaptation [PDF] [G-Scholar] [CODE] -
ITTA[Chen et al., Proc. CVPR 2023] Improved test-time adaptation for domain generalization [PDF] [G-Scholar] [CODE] -
TUR[Chen et al., Proc. ICCV 2023] Activate and reject: Towards safe domain generalization under category shift [PDF] [G-Scholar] -
VDP[Gan et al., Proc. AAAI 2023] Decorate the newcomers: Visual domain prompt for continual test time adaptation [PDF] [G-Scholar] -
FTTA[Huang et al., Proc. MICCAI 2023] Fourier test-time adaptation with multi-level consistency for robust classification [PDF] [G-Scholar] -
MTA[Wang et al., Proc. AI 2023] Multiple teacher model for continual test-time domain adaptation [PDF] [G-Scholar] -
TSOTTA[Mao et al., IEEE Sensors Journal 2023] Online test-time adaptation for patient-independent seizure prediction [PDF] [G-Scholar] -
...[Wu et al., arXiv 2023] Learning to adapt to online streams with distribution shifts [PDF] [G-Scholar] -
MTTT[Sun et al., arXiv 2023] Learning to (learn at test time) [PDF] [G-Scholar] [CODE] -
BESTTA[Cho et al., arXiv 2023] Beyond entropy: Style transfer guided single image continual test-time adaptation [PDF] [G-Scholar] -
...[Marsden et al., Proc. WACV 2024] Universal test-time adaptation through weight ensembling, diversity weighting, and prior correction [PDF] [G-Scholar] -
HKA[Liu et al., Proc. ICLR 2024] ViDA: Homeostatic visual domain adapter for continual test time adaptation [PDF] [G-Scholar] [CODE] -
...[Tomar et al., Proc. ICLR 2024] Un-mixing test-time normalization statistics: Combatting label temporal correlation [PDF] [G-Scholar] -
DeYO[Lee et al., Proc. ICLR 2024] Entropy is not enough for test-time adaptation: From the perspective of disentangled factors [PDF] [G-Scholar] -
FOA[Niu et al., Proc. ICML 2024] Test-time model adaptation with only forward passes [PDF] [G-Scholar] -
...[Alfarra et al., Proc. ICML 2024] Evaluation of test-time adaptation under computational time constraints [PDF] [G-Scholar--] [CODE] -
TDA[Karmanov et al., Proc. CVPR 2024] Efficient test-time adaptation of vision-language models [PDF] [G-Scholar] [CODE] -
DART[Liu et al., Proc. AAAI 2024] DART: Dual-modal adaptive online prompting and knowledge retention for test-time adaptation [PDF] [G-Scholar] -
ADAPROMPT[Zhang et al., Proc. AAAI 2024] Robust test-time adaptation for zero-shot prompt tuning [PDF] [G-Scholar] -
DCT[Tang et al., Proc. ACM MM 2024] Domain-conditioned transformer for fully test-time adaptation [PDF] [G-Scholar] -
GALA[Sahoo et al., Proc. NeurIPS Workshops 2024] A layer selection tpproach to test time adaptation [PDF] [G-Scholar--] -
LEAST[Sahoo et al., arXiv 2024] Layerwise early stopping for test time adaptation [PDF] [G-Scholar] -
ARC[Chen et al., arXiv 2024] Adaptive rentention & correction for continual learning [PDF] [G-Scholar] -
...[Tang et al., arXiv 2024] Learning visual conditioning tokens to correct domain shift for fully test-time adaptation [PDF] [G-Scholar] -
TAEA[Feng et al., arXiv 2024] Test-time alignment-Enhanced adapter for vision-language models [PDF] [G-Scholar] [CODE--]
-
OnAVOS[Voigtlaender and Leibe., Proc. BMVC 2017] Online adaptation of convolutional neural networks for video object segmentation [PDF] [G-Scholar] -
JITNet[Mullapudi et al., Proc. ICCV 2019] Online model distillation for efficient video inference [PDF] [G-Scholar] [CODE] -
TN-SIB[Zhang et al., Pattern Recognition 2022] Generalizable model-agnostic semantic segmentation via target-specific normalization [PDF] [G-Scholar] -
OASIS[Volpi et al., Proc. CVPR 2022] On the road to online adaptation for semantic image segmentation [PDF] [G-Scholar] [CODE] -
AuxAdapt[Zhang et al., Proc. WACV2022] AuxAdapt: Stable and efficient test-time adaptation for temporally consistent video semantic segmentation [PDF] [G-Scholar] -
FTEA[Zhang et al., arXiv 2022] Unseen object instance segmentation with fully test-time RGB-D embeddings adaptation [PDF] [G-Scholar] -
CoMAC[Cao et al., Proc. ICCV 2023] Multi-modal continual test-time adaptation for 3D semantic segmentation [PDF] [G-Scholar] -
Momentum Adapt[Hassankhani et al., Proc. BMVC 2023] Momentum adapt: Robust unsupervised adaptation for improving temporal consistency in video semantic segmentation during test-time [PDF] [G-Scholar--] -
TransAdapt[Das et al., Proc. ICASSP 2023] TransAdapt: A transformative framework for online test time adaptive semantic segmentation [PDF] [G-Scholar] -
SATTA[Zhang et al., Proc. MICCAI 2023] SATTA: Semantic-aware test-time adaptation for cross-domain medical image segmentation [PDF] [G-Scholar] -
PITTA[Li et al., Proc. ML4H 2023] Gradient-map-guided adaptive domain generalization for cross modality MRI segmentation [PDF] [G-Scholar] -
TestFit[Zhang et al., Medical Image Analysis 2023] TestFit: A plug-and-play one-pass test time method for medical image segmentation [PDF] [G-Scholar] -
SVDP[Yang et al., arXiv 2023] Exploring sparse visual prompt for cross-domain semantic segmentation [PDF] [G-Scholar] -
...[Wang et al., arXiv 2023] Test-time training on video streams [PDF] [G-Scholar] -
DAT[Ni et al., arXiv 2023] Distribution-aware continual test time adaptation for semantic segmentation [PDF] [G-Scholar] [CODE] -
...[Yi et al., arXiv 2023] A critical look at classic test-time adaptation methods in semantic segmentation [PDF] [G-Scholar] -
...[Sojka et al., arXiv 2023] Technical report for ICCV 2023 visual continual learning challenge: Continuous test-time adaptation for semantic segmentation [PDF] [G-Scholar] -
...[Yuan et al., arXiv 2023] Few clicks suffice: Active test-time adaptation for semantic segmentation [PDF] [G-Scholar] -
BECoTTA[Lee et al., Proc. ICML 2024] BECoTTA: Input-dependent online blending of experts for continual test-time adaptation [PDF] [G-Scholar] [CODE] -
VPTTA[Chen et al., Proc. CVPR 2024] Each test image deserves a specific prompt: Continual test-time adaptation for 2D medical Image segmentation [PDF] [G-Scholar] [CODE] -
HGL[Zou et al., Proc. ECCV 2024] HGL: Hierarchical geometry learning for test-time adaptation in 3D point cloud segmentation [PDF] [G-Scholar--] [CODE] -
...[Chen et al., Proc. ACM MM 2024] From question to exploration: Can classic test-time adaptation strategies be effectively applied in semantic segmentation? [PDF] [G-Scholar] -
...[Atanyan et al., Proc. WACV 2024] Continuous adaptation for interactive segmentation using teacher-student architecture [PDF] [G-Scholar] -
DoSe[Reddy et al., Proc. WACV 2024] Towards domain-aware knowledge distillation for continual model generalization [PDF] [G-Scholar--] -
...[Li et al., Intelligence, Informatics and Infrastructure 2024] Generalizing deep learning-based distress segmentation models for subway tunnel images by test-time training [PDF] [G-Scholar--] -
RODASS[Liu et al., arXiv 2024] Towards robust online domain adaptive semantic segmentation under adverse weather conditions [PDF] [G-Scholar] -
GraTa[Chen et al., Proc. AAAI 2025] Gradient alignment improves test-time adaptation for medical image segmentation [PDF] [G-Scholar] [CODE]
-
...[Lin et al., arXiv 2023] VCL challenges 2023 at ICCV 2023 technical report: Bi-level adaptation method for test-time adaptive object detection [PDF] [G-Scholar] -
...[Li et al., arXiv 2023] Domain generalization of 3D object detection by density-resampling [PDF] [G-Scholar] -
CETR[An et al., Proc. AAAI 2024] Context enhanced transformer for single image object detection in video data [PDF] [G-Scholar] [CODE--] -
PS-TTL[Gao et al., Proc. ACM MM 2024] PS-TTL: Prototype-based soft-labels and test-time learning for few-shot object detection [PDF] [G-Scholar] [CODE--] -
...[Etchegaray et al., Proc. IJCNN 2024] Edge Deployable online domain adaptation for underwater object detection [PDF] [G-Scholar--] -
MLFA[Liu et al., IEEE TIP 2024] MLFA: Towards realistic test time adaptive object detection by multi-level feature alignment [PDF] [G-Scholar] [CODE] -
WSTTA[Doan et al., arXiv 2024] Weakly supervised test-time domain adaptation for object detection [PDF] [G-Scholar] [CODE--] -
CTAOD[Cao et al., arXiv 2024] Exploring test-time adaptation for object detection in continually changing environments [PDF] [G-Scholar]
-
BoostAdapter[Zhang et al., Proc. NeurIPS 2024] BoostAdapter: Improving vision-language test-time adaptation via regional bootstrapping [PDF] [G-Scholar--] [CODE--] -
DPE[Zhang et al., Proc. NeurIPS 2024] Dual prototype evolving for test-time generalization of vision-language models [PDF] [G-Scholar] [CODE] -
DMN-ZS[Zhang et al., Proc. CVPR 2024] Dual memory networks: A versatile adaptation approach for vision-language models [PDF] [G-Scholar] [CODE] -
OnZeta[Qian and Hu, Proc. ECCV 2024] Online zero-shot classification with CLIP [PDF] [G-Scholar] [CODE] -
Dota[Han et al., arXiv 2024] DOTA: Distributional test-time adaptation of vision-language models [PDF] [G-Scholar] -
scFusionTTT[Meng et al., arXiv 2024] scFusionTTT: Single-cell transcriptomics and proteomics fusion with test-time training layers [PDF] [G-Scholar] [CODE--]
-
ViTTA[Lin et al., Proc. CVPR 2023] Video test-time adaptation for action recognition [PDF] [G-Scholar] [CODE--] -
AME[Zeng et al., Proc. ACMMM 2023] Exploring motion cues for video test-time adaptation [PDF] [G-Scholar]
-
BOA[Guan et al., Proc. CVPR 2021] Bilevel online adaptation for out-of-domain human mesh reconstruction [PDF] [G-Scholar] [CODE] -
...[Kundu et al., Proc. CVPR 2022] Uncertainty-aware adaptation for self-supervised 3D human pose estimation [PDF] [G-Scholar] -
...[Ayyoubzadeh et al., IEEE TIP 2023] Test-time adaptation for optical flow estimation using motion vectors [PDF] [G-Scholar] -
ATTA[Gao et al., Proc. NeurIPS 2023] ATTA: Anomaly-aware test-time adaptation for out-of-distribution detection in segmentation [PDF] [G-Scholar] [CODE--] -
H/P-TTP[Cui et al., Proc. ICCV 2023] Test-time personalizable forecasting of 3D human poses [PDF] [G-Scholar] -
OnDA-DETR[Suzuki et al., Proc. ICIP 2023] OnDA-DETR: Online domain adaptation for detection transformers with self-training framework [PDF] [G-Scholar--] -
...[Huang et al., Proc. BIBM 2023] Huang A parameter adaptive tuning algorithm for medical image recognition model testing [PDF] [G-Scholar] -
AUTO[Yang et al., arXiv 2023] AUTO: Adaptive outlier optimization for online test-time OOD detection [PDF] [G-Scholar] -
...[Lumentut and Lee, arXiv 2023] 3DHR-Co: A collaborative test-time refinement framework for in-the-wild 3D human-body reconstruction task [PDF] [G-Scholar] -
AdaODD[Zhang et al., arXiv 2023] Model-free test time adaptation for out-of-distribution detection [PDF] [G-Scholar] -
FSTTA[Gao et al., Proc. ICML 2024] Fast-slow test-time adaptation for online vision-and-language navigation [PDF] [G-Scholar] [CODE] -
AdaptOD[Miao et al., Proc. NeurIPS 2024] Long-tailed out-of-distribution detection via normalized outlier distribution adaptation [PDF] [G-Scholar] [CODE--] -
RTL[Fan et al., Proc. CVPR 2024] Test-time linear out-of-distribution detection [PDF] [G-Scholar] [CODE] -
2LTTA[Lei and Pernkopf, Proc. ICML Workshops 2024] Two-level test-time adaptation in multimodal learning [PDF] [G-Scholar] -
...[Song et al., Proc. ICPR 2024] Source-free test-time adaptation for online surface-defect detection [PDF] [G-Scholar] -
...[Borkar et al., Proc. ICVGIP 2024] No prompting frozen foundation models: Interactive medical volume segmentation using continual test time adaptation of compact models [PDF] [G-Scholar--] -
STA-AD[Ambekar et al., Proc. MICCAI Workshops 2024] Selective test-time adaptation for unsupervised anomaly detection using neural implicit representations [PDF] [G-Scholar] [CODE] -
ADCSD[Guo et al., arXiv 2024] Online test-time adaptation of spatial-temporal traffic flow forecasting [PDF] [G-Scholar] [CODE] -
MiDl[Ramazanova et al., arXiv 2024] Combating missing modalities in egocentric videos at test time [PDF] [G-Scholar] -
ROSITA[Sreenivas and Biswas, arXiv 2024] Effectiveness of vision language models for open-world single image test time adaptation [PDF] [G-Scholar] [CODE]
-
ONDA[Mancini et al., Proc. IROS 2018] Kitting in the wild through online domain adaptation [PDF] [G-Scholar] -
Tent[Sun et al., Proc. ICLR 2021] Tent: Fully test-time adaptation by entropy minimization [PDF] [G-Scholar] [CODE] -
BACS[Zhou and Levine, Proc. NeurIPS 2021] Bayesian adaptation for covariate shift [PDF] [G-Scholar] -
TTA-PR[Sivaprasad and Fleuret, Proc. NeurIPS Workshops 2021] Test time adaptation through perturbation robustness [PDF] [G-Scholar] -
Core (alpha-BN)[You et al., arXiv 2021] Test-time batch statistics calibration for covariate shift [PDF] [G-Scholar] -
SLR+IT[Mummadi et al., arXiv 2021] Test-time adaptation to distribution shift by confidence maximization and input transformation [PDF] [G-Scholar] -
MixNorm[Hu et al., arXiv 2021] MixNorm: Test-time adaptation through online normalization estimation [PDF] [G-Scholar]
-
EATA[Niu et al., Proc. ICML 2022] Efficient test-time model adaptation without forgetting [PDF] [G-Scholar] [CODE] -
VMP[Jing et al., Proc. NeurIPS 2022] Variational model perturbation for source-free domain adaptation [PDF] [G-Scholar] [CODE] -
TTAC[Su et al., Proc. NeurIPS 2022] Revisiting realistic test-time training: Sequential inference and adaptation by anchored clustering [PDF] [G-Scholar] [CODE] -
Conjugate PL[Goyal et al., Proc. NeurIPS 2022] Test-time adaptation via conjugate pseudo-labels [PDF] [G-Scholar] [CODE] -
DUA[Mirza et al., Proc. CVPR 2022] The norm must go on: Dynamic unsupervised domain adaptation by normalization [PDF] [G-Scholar] [CODE] -
LAME[Boudiaf et al., Proc. CVPR 2022] Parameter-free online test-time adaptation [PDF] [G-Scholar] [CODE] -
SWR-NSP[Choi et al., Proc. ECCV 2022] Improving test-time adaptation via shift-agnostic weight regularization and nearest source prototypes [PDF] [G-Scholar] -
CFA[Kojima et al., Proc. IJCAI 2022] Robustifying vision transformer without retraining from scratch by test-time class-conditional feature alignment [PDF] [G-Scholar] [CODE] -
MuSLA[Kingetsu et al., Proc. ICIP 2022] Multi-step test-time adaptation with entropy minimization and pseudo-labeling [PDF] [G-Scholar] -
...[Bhardwaj et al., Proc. ISPASS 2022] Benchmarking test-time unsupervised deep neural network adaptation on edge devices [PDF] [G-Scholar] -
...[Bhardwaj et al., Proc. DATE 2022] Unsupervised test-time adaptation of deep neural networks at the edge: a case study [PDF] [G-Scholar] -
DLTTA[Yang et al., IEEE TMI 2022] DLTTA: Dynamic learning rate for test-time adaptation on cross-domain medical images [PDF] [G-Scholar] [CODE] -
...[Kerssies et al., arXiv 2022] Evaluating continual test-time adaptation for contextual and semantic domain shifts [PDF] [G-Scholar] -
CAFA[Jung et al., arXiv 2022] CAFA: Class-aware feature alignment for test-time adaptation [PDF] [G-Scholar] -
AdaODM[Zhang and Chen, arXiv 2022] Adaptive domain generalization via online disagreement minimization [PDF] [G-Scholar]
-
TAST[Jang and Chung, Proc. ICLR 2023] Test-time adaptation via self-training with nearest neighbor information [PDF] [G-Scholar] -
...[Wang and Wibisono, Proc. ICLR 2023] Towards understanding GD with hard and conjugate pseudo-labels for test-time adaptation [PDF] [G-Scholar] -
MECTA[Hong et al., Proc. ICLR 2023] MECTA: Memory-economic continual test-time model adaptation [PDF] [G-Scholar] -
DELTA[Zhao et al., Proc. ICLR 2023] DELTA: Degradation-free fully test-time adaptation [PDF] [G-Scholar] -
...[Kang et al., Proc. ICML 2023] Leveraging proxy of training data for test-time adaptation [PDF] [G-Scholar] -
...[Zhao et al., Proc. ICML 2023] On pitfalls of test-time adaptation [PDF] [G-Scholar]~~ [Zhao et al., Proc. ICLR Workshops 2023] On pitfalls of test-time adaptation [PDF] [G-Scholar]~~
-
ODS[Zhou et al., Proc. ICML 2023] ODS: Test-time adaptation in the presence of open-world data shift [PDF] [G-Scholar] -
CCC[Press et al., Proc. NeurIPS 2023] RDumb: A simple approach that questions our progress in continual test-time adaptation [PDF] [G-Scholar] [CODE] -
SoTTA[Gong et al., Proc. NeurIPS 2023] SoTTA: Robust test-time adaptation on noisy data streams [PDF] [G-Scholar] [CODE] -
FedICON[Tan et al., Proc. NeurIPS 2023] Is heterogeneity notorious? Taming heterogeneity to handle test-time shift in federated learning [PDF] [G-Scholar--] -
ActMAD[Mirza et al., Proc. CVPR 2023] ActMAD: Activation matching to align distributions for test-time-training [PDF] [G-Scholar] [CODE] -
RMT[Döbler et al., Proc. CVPR 2023] Robust mean teacher for continual and gradual test-time adaptation [PDF] [G-Scholar] [CODE] -
PETAL[Brahma and Rai, Proc. CVPR 2023] A probabilistic framework for lifelong test-time adaptation [PDF] [G-Scholar] [CODE] -
NHL[Tang et al., Proc. CVPR 2023] Neuro-modulated hebbian learning for fully test-time adaptation [PDF] [G-Scholar] -
EcoTTA[Song et al., Proc. CVPR 2023] EcoTTA: Memory-efficient continual test-time adaptation via self-distilled regularization [PDF] [G-Scholar] -
TIPI[Nguyen et al., Proc. CVPR 2023] TIPI: Test time adaptation with transformation invariance [PDF] [G-Scholar] -
RoTTA[Yuan et al., Proc. CVPR 2023] Robust test-time adaptation in dynamic scenarios [PDF] [G-Scholar] [CODE] -
TeSLA[Tomar et al., Proc. CVPR 2023] TeSLA: Test-time self-learning with automatic adversarial augmentation [PDF] [G-Scholar] -
MSLC-TSD[Wang et al., Proc. CVPR 2023] Feature alignment and uniformity for test-time adaptation [PDF] [G-Scholar] -
OWTTT[Li et al., Proc. ICCV 2023] On the robustness of open-world test-time training: Self-training with dynamic prototype expansion [PDF] [G-Scholar] [CODE--] -
OCR[Li et al., Proc. ICCV 2023] Order-preserving consistency regularization for domain adaptation and generalization [PDF] [G-Scholar] [CODE--] -
...[Yang et al., Proc. IJCAI 2023] Exploring safety supervision for continual test-time domain adaptation [PDF] [G-Scholar] -
...[Yu et al., Proc. ACMMM 2023] Noise-robust continual test-time domain adaptation [PDF] [G-Scholar] [CODE] -
...[Narayanan et al., Proc. ICLR Workshops 2023] A simple test-time adaptation method for source-free domain generalization [PDF] [G-Scholar--] -
DSS[Chakrabarty et al., Proc. ICLR Workshops 2023] Domain shift signal for low resource continuous test-time adaptation [PDF] [G-Scholar--] -
JumpStyle[Singh et al., Proc. ICLR Workshops 2023] JumpStyle: A framework for data-efficient online adaptation [PDF] [G-Scholar--] -
D-TAPE[Raman et al., Proc. NeurIPS Workshops 2023] Turn down the noise: Leveraging diffusion models for test-time adaptation via pseudo-label ensembling [PDF] [G-Scholar] -
...[Chakrabarty et al., Proc. ICCV Workshops 2023] A simple signal for domain shift [PDF] [G-Scholar] -
CAFe[Adachi et al., Proc. ICIP 2023] Covariance-aware feature alignment with pre-computed source statistics for test-time adaptation to multiple image corruptions [PDF] [G-Scholar] -
...[Rifat et al., Proc. MILCOM 2023] Zero-shot dynamic neural network adaptation in tactical wireless systems [PDF] [G-Scholar--] -
AWMC[Lee et al., Proc. ASRU 2023] AWMC: Online test-time adaptation without mode collapse for continual adaptation [PDF] [G-Scholar--]
-
T-TIME[Li et al., IEEE TMBE 2023] T-TIME: Test-time information maximization ensemble for plug-and-play BCIs [PDF] [G-Scholar] [CODE] -
OTA[Zhou et al., Journal of Software 2023] Towards robust test-time adaptation for open-set recognition [PDF] [G-Scholar] -
CSTTA[Yang et al., Knowledge-Based Systems 2023] Confidence-based and sample-reweighted test-time adaptation [PDF] [G-Scholar--] -
GpreBN[Yang et al., arXiv 2023] Gradient preserving batch normalization for test-time adaptation [PDF] [G-Scholar]- [Yang et al., arXiv 2022] Test-time batch normalization [PDF] [G-Scholar] -
ECL[Han et al., arXiv 2023] Rethinking precision of pseudo label: Test-time adaptation via complementary learning [PDF] [G-Scholar] -
TTAC++[Su et al., arXiv 2023] Revisiting realistic test-time training: Sequential inference and adaptation by anchored clustering regularized self-training [PDF] [G-Scholar] -
...[Alfarra et al., arXiv 2023] Revisiting test time adaptation under online evaluation [PDF] [G-Scholar] [CODE] -
SATA[Chakrabarty et al., arXiv 2023] SATA: Source anchoring and target alignment network for continual test time adaptation [PDF] [G-Scholar] -
...[ Jahan and Savakis, arXiv 2023] Continual domain adaptation on aerial images under gradually degrading weather [PDF] [G-Scholar--] -
...[Du et al., arXiv 2023] Domain adaptation for satellite-borne hyperspectral cloud detection [PDF] [G-Scholar] -
AR-TTA[Sójka et al., arXiv 2023] AR-TTA: A simple method for real-world continual test-time adaptation [PDF] [G-Scholar] -
GRoTTA[Li et al., arXiv 2023] Generalized robust test-time adaptation in continuous dynamic scenarios [PDF] [G-Scholar] -
...[Kim et al., arXiv 2023] Reliable test-time adaptation via agreement-on-the-line [PDF] [G-Scholar] -
UniDG[Zhang et al., arXiv 2023] Towards unified and effective domain generalization [PDF] [G-Scholar] [CODE] -
TTC[Lin et al., arXiv 2023] Improving entropy-based test-time adaptation from a clustering view [PDF] [G-Scholar] -
PeTTA[Hoang et al., arXiv 2023] Persistent test-time adaptation in episodic testing scenarios [PDF] [G-Scholar] -
...[Csaba et al., arXiv 2023] Label delay in continual learning [PDF] [G-Scholar] -
ADMA[Liu et al., arXiv 2023] Adaptive distribution masked autoencoders for continual test-time adaptation [PDF] [G-Scholar--] -
VPL[Ambekar et al., Misc 2023] Variational pseudo labels for meta test-time adaptation [PDF] [G-Scholar] -
BaFTA[Hu et al., Misc 2023] BaFTA: Backprop-free test-time adaptation for zero-shot vision language models [PDF] [G-Scholar--]
-
SimATTA[Gui et al., Proc. ICLR 2024] Active test-time adaptation: Theoretical analyses and an algorithm [PDF] [G-Scholar] [CODE--] -
CEMA[Chen et al., Proc. ICLR 2024] Towards robust and efficient cloud-edge elastic model adaptation via selective entropy distillation [PDF] [G-Scholar] -
PROGRAM[Sun et al., Proc. ICLR 2024] PROGRAM: Prototype graph model based pseudo-label learning for test-time adaptation [PDF] [G-Scholar] -
CMF[Lee and Chang, Proc. ICLR 2024] Continual momentum filtering on parameter space for online test-time adaptation [PDF] [G-Scholar] -
SLWI[Lee and Chang, Proc. ICML 2024] Stationary latent weight inference for unreliable observations from online test-time adaptation [PDF] [G-Scholar] -
DUSA[Li et al., Proc. NeurIPS 2024] Exploring structured semantic priors underlying diffusion score for test-time adaptation [PDF] [G-Scholar--] [CODE--] -
MGTTA[Zhang et al., Proc. NeurIPS 2024] Test-time adaptation in non-stationary environments via adaptive representation alignment [PDF] [G-Scholar--] -
BFTT3D[Wang et al., Proc. CVPR 2024] Backpropagation-free network for 3D test-time adaptation [PDF] [G-Scholar] [CODE--] -
UniEnt[Gao et al., Proc. CVPR 2024] Unified entropy optimization for open-set test-time adaptation [PDF] [G-Scholar] [CODE] -
DPLOT[Yu et al., Proc. CVPR 2024] Domain-specific block selection and paired-view pseudo-labeling for online test-time adaptation [PDF] [G-Scholar] [CODE] -
ADMA[Liu et al., Proc. CVPR 2024] Continual-MAE: Adaptive distribution masked autoencoders for continual test-time adaptation [PDF] [G-Scholar] -
...[Yang et al., Proc. CVPR 2024] A versatile framework for continual test-time domain adaptation: Balancing discriminability and generalizability [PDF] [G-Scholar] -
IST4TTA[Ma, Proc. CVPR 2024] Improved self-training for test-time adaptation [PDF] [G-Scholar] [CODE] -
OBAO[Zhu et al., Proc. ECCV 2024] Reshaping the online data buffering and organizing mechanism for continual test-time adaptation [PDF] [G-Scholar] [CODE--] -
DA-TTA[Wang et al., Proc. ECCV 2024] Distribution alignment for fully test-time adaptation with dynamic online data streams [PDF] [G-Scholar] [CODE--] -
STAMP[Yu et al., Proc. ECCV 2024] STAMP: Outlier-aware test-time adaptation with stable memory replay [PDF] [G-Scholar] [CODE] -
DPAL[Tang et al., Proc. ECCV 2024] Dual-path adversarial lifting for domain shift correction in online test-time adaptation [PDF] [G-Scholar] [CODE] -
PSDG[Yang et al., Proc. KDD 2024] Practical single domain generalization via training-time and test-time learning [PDF] [G-Scholar--] -
CETA[Yang et al., Proc. KDD 2024] Towards test time adaptation via calibrated entropy minimization [PDF] [G-Scholar] -
TSA[Zhang et al., Proc. KDD 2024] Enabling collaborative test-time adaptation in dynamic environment via federated learning [PDF] [G-Scholar] [CODE] -
TRIBE[Su et al., Proc. AAAI 2024] Towards real-world test-time adaptation: Tri-Net self-training with balanced normalization [PDF] [G-Scholar] [CODE] -
...[Su et al., Proc. AAAI 2024] Singular value penalization and semantic data augmentation for fully test-time adaptation [PDF] [G-Scholar] -
TEMA[Su et al., Proc. AAAI 2024] Unraveling batch normalization for realistic test-time adaptation [PDF] [G-Scholar] [CODE] -
...[Yang et al., Proc. IJCAI 2024] Navigating continual test-time adaptation with symbiosis knowledge [PDF] [G-Scholar--] -
ATTA[Jia et al, Proc. IJCAI 2024] ATTA: Adaptive test-time adaptation for multi-modal sleep stage classification [PDF [G-Scholar--] -
CNA-TTA[Cho et al., Proc. ACCV 2024] CNG-SFDA: Clean-and-noisy region guided online-offline source-free domain adaptation [PDF] [G-Scholar] [CODE] -
DSS[Wang et al., Proc. WACV 2024] Continual test-time domain adaptation via dynamic sample selection [PDF] [G-Scholar] -
...[Mounsaveng et al., Proc. WACV 2024] Bag of tricks for fully test-time adaptation [PDF] [G-Scholar] -
pSTarC[Sreenivas et al., Proc. WACV 2024] pSTarC: Pseudo source guided target clustering for fully test-time adaptation [PDF] [G-Scholar] -
REALM[Seto et al., Proc. WACV 2024] REALM: Robust entropy adaptive loss minimization for improved single-sample test-time adaptation [PDF] [G-Scholar] -
...[Niloy et al., Proc. WACV 2024] Effective restoration of source knowledge in continual test time adaptation [PDF] [G-Scholar] -
LayerwiseTTA[Park et al., Proc. WACV 2024] Layer-wise auto-weighting for non-stationary test-time adaptation [PDF] [G-Scholar] [CODE] -
...[Choi et al., Proc. ICML Workshops 2024] Adaptive concept bottleneck for foundation models [PDF] [G-Scholar] -
M-TENT[Chatterjee et al., Proc. NeurIPS Workshops 2024] Analysing softmax entropy minimization for adaptating multitask models at test-time [PDF] [G-Scholar--] -
PeTTA[Hoang et al., Proc. CVPR Workshops 2024] Persistent test-time adaptation in recurring testing scenarios [PDF] [G-Scholar] [CODE--] -
MCTTA[Yamashita and Hotta, Proc. CVPR Workshops 2024] MixStyle-based contrastive test-time adaptation: Pathway to domain generalization [PDF] [G-Scholar] -
FACTTA[Wu and Zhang, Proc. ACMMM Workshops 2024] Fast and accurate continual test time domain adaptation [PDF] [G-Scholar] -
DAB[Döbler et al., Proc. ICASSP 2024] Diversity-aware buffer for coping with temporally correlated data streams in online test-time adaptation [PDF] [G-Scholar] -
TESLA[Cha et al., Proc. MOBISYS 2024] Poster: Time-efficient sparse and lightweight adaptation for real-time mobile application [PDF] [G-Scholar] -
TECA[Enomoto et al., Proc. IJCNN 2024] Test-time adaptation meets image enhancement: Improving accuracy via uncertainty-aware logit switching [PDF] [G-Scholar] -
ORRIC[Cai et al., Proc. IEEE INFOCOM 2024] Online resource allocation for edge intelligence with colocated model retraining and inference [PDF] [G-Scholar] -
TNN[Ambekar et al., Proc. MICCAI Workshops 2024] Non-parametric neighborhood test-time generalization: Application to medical image classification [PDF] [G-Scholar--] [CODE] -
...[Wang et al., Proc. IEEE CASE 2024] In-Situ 3D printing monitoring in dynamic environments via self-supervised deep neural network adaptation [PDF] [G-Scholar--] -
RDPT[Xiong and Yang, Proc. IEEE CSCWD 2024] Test-time adaptation with robust dual-stream perturbation for stable agent deployment in dynamic scenarios [PDF] [G-Scholar--] [CODE] -
FATA[Jiang et al., Proc. BigDIA 2024] FATA: Focal-adjusted test-time adaptation under data imbalance [PDF] [G-Scholar--] -
TPM[Gu et al., IJCV 2024] Adversarial reweighting with α-power maximization for domain adaptation [PDF] [G-Scholar] [CODE] -
ElasticDNN[Zhang et al., IEEE TC 2024] ElasticDNN: On-device neural network remodeling for adapting evolving vision domains at edge [PDF] [G-Scholar] -
FTTA[Wang et al., IEEE TFUZZ 2024] Fuzzy rule-based test-time adaptation for class imbalance in dynamic scenarios [PDF] [G-Scholar--] -
...[Wu et al., IEEE TII 2024] Online adaptive fault diagnosis with test-time domain adaptation [PDF] [G-Scholar--] -
L^CE-LoSwRot[Jhong et al., IEEE TCE 2024] An edge-cloud collaborative scalp inspection system based on robust representation learning [PDF] [G-Scholar--] -
NLS[Yang et al., Neurocomputing 2024] Towards test time domain adaptation via negative label smoothing [PDF] [G-Scholar] -
CPA[Lee et al., Pattern Recognition Letters 2024] Prototypical class-wise test-time adaptation [PDF] [G-Scholar] -
CIM[Fan et al., Journal on Autonomous Transportation Systems 2024] Benchmarking test-time DNN adaptation at edge with compute-in-memory [PDF] [G-Scholar] [CODE] -
...[Wen et al., Journal of Electronic Imaging 2024] Test-time adaptation via self-training with future information [PDF] [G-Scholar] -
RGAR[Xiong and Xiang, The Visual Computer 2024] Robust gradient aware and reliable entropy minimization for stable test-time adaptation in dynamic scenarios [PDF] [G-Scholar--] -
SAFTTA[Li and Yang, IEEE Access 2024] Smooth guided adversarial fully test-time adaptation [PDF] [G-Scholar--] -
CycleTTA[Jiang et al., Mathematics 2024] Advancing model generalization in continuous cyclic test-time adaptation with matrix perturbation noise [PDF] [G-Scholar] -
MeTA[Ahmed et al., arXiv 2024] MeTA: Multi-source test time adaptation [PDF] [G-Scholar] -
PLUTO[Chang et al., arXiv 2024] Plug-and-play transformer modules for test-time adaptation [PDF] [G-Scholar] -
DPL[Wang et al., arXiv 2024] Decoupled prototype learning for reliable test-time adaptation [PDF] [G-Scholar] -
ResiTTA[Zhou et al., arXiv 2024] Resilient practical test-time adaptation: Soft batch normalization alignment and entropy-driven memory bank [PDF] [G-Scholar] -
GAP[Shin et al., arXiv 2024] Gradient alignment with prototype feature for fully test-time adaptation [PDF] [G-Scholar] -
VCoTTA[Lyu et al., arXiv 2024] Variational continual test-time adaptation [PDF] [G-Scholar] -
...[Chung et al., arXiv 2024] Mitigating the bias in the model for continual test-time adaptation [PDF] [G-Scholar] -
EATA-C[Tan et al., arXiv 2024] Uncertainty-calibrated test-time model adaptation without forgetting [PDF] [G-Scholar] -
CODA[Qiu et al., arXiv 2024] CODA: A cost-efficient test-time domain adaptation mechanism for HAR [PDF] [G-Scholar] -
HILTTA[Li et al., arXiv 2024] Exploring human-in-the-loop test-time adaptation by synergizing active learning and model selection [PDF] [G-Scholar] -
MoASE[Zhang et al., arXiv 2024] Decomposing the neurons: Activation sparsity via mixture of experts for continual test time adaptation [PDF] [G-Scholar] [CODE] -
C-CoTTA[Shi et al., arXiv 2024] Controllable continual test-time adaptation [PDF] [G-Scholar] [CODE] -
PLF[Tan et al., arXiv 2024] Less is more: Pseudo-label filtering for continual test-time adaptation [PDF] [G-Scholar] [CODE--] -
DYN[Jiang et al., arXiv 2024] Discover your neighbors: Advanced stable test-time adaptation in dynamic world [PDF] [G-Scholar] -
DPCore[Zhang et al., arXiv 2024] Dynamic domains, dynamic solutions: DPCore for continual test-time adaptation [PDF] [G-Scholar--] [CODE--] -
...[Nguyen et al., arXiv 2024] Adaptive cascading network for continual test-time adaptation [PDF] [G-Scholar] -
TPD[Zeng et al., arXiv 2024] Graph-guided test-time adaptation for glaucoma diagnosis using fundus photography [PDF] [G-Scholar] -
...[Cygert et al., arXiv 2024] Realistic evaluation of test-time adaptation algorithms: Unsupervised hyperparameter selection [PDF] [G-Scholar] -
DATTA[Ye et al., arXiv 2024] DATTA: Towards diversity adaptive test-time adaptation in dynamic wild world [PDF] [G-Scholar--] -
PSMT[Tian and Lyu, arXiv 2024] Parameter-selective continual test-time adaptation [PDF] [G-Scholar] [CODE] -
UniTTA[Du et al., arXiv 2024] UniTTA: Unified benchmark and versatile framework towards realistic test-time adaptation [PDF] [G-Scholar] [CODE--] -
STAD[Schirmer et al., arXiv 2024] Test-time adaptation with state-space models [PDF] [G-Scholar] -
POEM[Bar et al., arXiv 2024] Protected test-time adaptation via online entropy matching: A betting approach [PDF] [G-Scholar] [CODE] -
FS-TTA[Luo et al., arXiv 2024] Enhancing test time adaptation with few-shot guidance [PDF] [G-Scholar] -
...[Duan et al., arXiv 2024] Brain-inspired online adaptation for remote sensing with spiking neural network [PDF] [G-Scholar] -
OWDCL[Su et al., arXiv 2024] Open-world test-time training: Self-training with contrast learning [PDF] [G-Scholar] -
DDSD[Park et al., arXiv 2024] Hybrid-TTA: Continual test-time adaptation via dynamic domain shift detection [PDF] [G-Scholar] -
ETAGE[Shamsi et al., arXiv 2024] ETAGE: Enhanced test time adaptation with integrated entropy and gradient norms for robust model performance [PDF] [G-Scholar] [CODE] -
DARDA[Rifat et al., arXiv 2024] DARDA: Domain-aware real-time dynamic neural network adaptation [PDF] [G-Scholar] -
Meta-TTT[Tao et al., arXiv 2024] Meta-TTT: A meta-learning minimax framework for test-time training [PDF] [G-Scholar] -
COME[Zhang et al., arXiv 2024] COME: Test-time adaption by conservatively minimizing entropy [PDF] [G-Scholar] -
FATA[Cho et al., arXiv 2024] Feature augmentation based test-time adaptation [PDF] [G-Scholar] -
TCR[Sun et al., arXiv 2024] Test-time adaptation for cross-modal retrieval with query shift [PDF] [G-Scholar] -
MDAA[Zhang et al., arXiv 2024] Analytic continual test-time adaptation for multi-modality corruption [PDF] [G-Scholar] -
TTVD[Lei et al., arXiv 2024] TTVD: Towards a geometric framework for test-time adaptation based on voronoi diagram [PDF] [G-Scholar] -
DART[Jang and Chung, arXiv 2024] Label distribution shift-aware prediction refinement for test-time adaptation [PDF] [G-Scholar] -
ASR[Wang et al., arXiv 2024] Maintain plasticity in long-timescale continual test-time adaptation [PDF] [G-Scholar] -
...[Cygert et al., Misc 2024] Realistic evaluation of test-time adaptation: Surrogate-based model selection strategies [PDF] [G-Scholar--] -
...[Gwon et al., Misc 2024] Refining pseudo labels for robust test time adaptation [PDF] [G-Scholar--] -
TTAC[Su et al., Misc 2024] Towards inference stage robust 3D point cloud recognition [PDF] [G-Scholar--]
-
PALM[Maharana et al., Proc. AAAI 2025] PALM: Pushing adaptive learning rate mechanisms for continual test-time adaptation [PDF] [G-Scholar] -
MGTTA[Deng et al., Proc. AAAI 2025] Learning to generate gradients for test-time adaptation via test-time training layers [PDF] [G-Scholar--] [CODE--] -
...[Si et al., Proc. ICASSP 2025] Generalize your face forgery detectors: An insertable adaptation module is all you need [PDF] [G-Scholar]
-
TePA[Cong et al., Proc. S&P 2024] Test-time poisoning attacks against test-time adaptation models [PDF] [G-Scholar] [CODE] -
RTTDP[Su et al., arXiv 2024] On the adversarial risk of test time adaptation: An investigation into realistic test-time data poisoning [PDF] [G-Scholar]
-
SwapPrompt[Ma et al., Proc. NeurIPS 2023] SwapPrompt: Test-time prompt adaptation for vision-language models [PDF] [G-Scholar] -
HisTPT[Zhang et al., Proc. NeurIPS 2024] Historical test-time prompt tuning for vision foundation models [PDF] [G-Scholar] -
VTE[Döbler et al., Proc. CVPR Workshops 2024] A lost opportunity for vision-language models: A comparative study of online test-time adaptation for vision-language models [PDF] [G-Scholar] [CODE] -
PCoTTA[Wang et al., Proc. IJCNN 2024] Prompt-Based memory bank for continual test-time domain adaptation in vision-language models [PDF] [G-Scholar--] -
PCPT[Wang et al., Pattern Recognition 2024] CTPT: Continual test-time prompt tuning for vision-language models [PDF] [G-Scholar--] -
CLIPArTT[Hakim et al., arXiv 2024] CLIPArTT: Light-weight adaptation of CLIP to new domains at test time [PDF] [G-Scholar] [CODE] -
BAT-CLIP[Maharana et al., arXiv 2024] Enhancing robustness of CLIP to common corruptions through bimodal test-time adaptation [PDF] [G-Scholar]
-
RNCR[Hu et al., Proc. MICCAI 2021] Fully test-time adaptation for image segmentation [PDF] [G-Scholar] -
...[Kuznietsov et al., Proc. WACV Workshops 2022] Towards unsupervised online domain adaptation for semantic segmentation [PDF] [G-Scholar] -
MM-TTA[Shin et al., Proc. CVPR 2022] MM-TTA: Multi-modal test-time adaptation for 3D semantic segmentation [PDF] [G-Scholar] [CODE--] -
CD-TTA[Song et al., arXiv 2022] CD-TTA: Compound domain test-time adaptation for semantic segmentation [PDF] [G-Scholar] -
...[Lee et al., Proc. ICCV 2023] Towards open-set test-time adaptation utilizing the wisdom of crowds in entropy minimization [PDF] [G-Scholar] -
OAST[Su et al., Proc. ICCV 2023] Unsupervised video object segmentation with online adversarial self-tuning [PDF] [G-Scholar--] -
3A-TTA[Huang et al., Proc. BMVC 2023] Test-time adaptation for robust face anti-spoofing [PDF] [G-Scholar--] -
...[Zhu et al., Proc. MICCAI 2023] Uncertainty and shape-aware continual test-time adaptation for cross-domain segmentation of medical images [PDF] [G-Scholar] [CODE--] -
...[Zhao et al., Proc. ICIG 2023] Revisiting TENT for test-time adaption semantic segmentation and classification head adjustment [PDF] [G-Scholar] -
Night-TTA[Liu et al., IEEE TAI 2023] Test-time adaptation for nighttime color-thermal semantic segmentation [PDF] [G-Scholar] -
...[Song et al., IEEE Robotics and Automation Letters 2023] Test-time adaptation in the dynamic world with compound domain knowledge management [PDF] [G-Scholar] -
MCDA[Ye et al., arXiv 2023] Multi task consistency guided source-free test-time domain adaptation medical image segmentation [PDF] [G-Scholar] -
OCL[Zhang et al., arXiv 2023] Test-time training for semantic segmentation with output contrastive loss [PDF] [G-Scholar] [CODE] -
SVDP[Yang et al., Proc. AAAI 2024] Exploring sparse visual prompt for domain adaptive dense prediction [PDF] [G-Scholar] -
MSC-TTA[Gérin et al., Proc. CVPR Workshops 2024] Multi-stream cellular test-time adaptation of real-time models evolving in dynamic environments [PDF] [G-Scholar] [CODE] -
MUTE[Du et al., ICLR Workshops 2024] Multi-source fully test-time adaptation [PDF] [G-Scholar--] -
STTA[Li et al., Proc. MICCAI 2024] Cache-driven spatial test-time adaptation for cross-modality medical image segmentation [PDF] [G-Scholar] [CODE--] -
DyNo[Fu et al., Proc. MICCAI Workshops 2024] DyNo: Dynamic normalization based test-time adaptation for 2D medical image segmentation [PDF] [G-Scholar--] [CODE] -
...[Niloy et al., Proc. ICASSP 2024] Source-free online domain adaptive semantic segmentation of satellite images under image degradation [PDF] [G-Scholar] -
USP[Wang et al., Remote Sensing 2024] Exploring uncertainty-based self-prompt for test-time adaptation semantic segmentation in remote sensing images [PDF] [G-Scholar] -
COMET[Schlachter and Yang, arXiv 2024] COMET: Contrastive mean teacher for online source-free universal domain adaptation [PDF] [G-Scholar] -
BECoTTA[Lee et al., arXiv 2024] BECoTTA: Input-dependent online blending of experts for continual test-time adaptation [PDF] [G-Scholar] [CODE] -
RetiGen[Chen et al., arXiv 2024] Active learning guided federated online adaptation: Applications in medical image segmentation [PDF] [G-Scholar] [CODE--] -
CoMM[Chuah et al, arXiv 2024] Enhanced online test-time adaptation with feature-weight cosine alignment [PDF] [G-Scholar] [CODE] -
...[Wang et al., arXiv 2024] Test-time adaptation for geospatial point cloud semantic segmentation with distinct domain shifts [PDF] [G-Scholar]
-
STFAR[Chen et al., arXiv 2023] STFAR: Improving object detection robustness at test-time by self-training with feature alignment regularization [PDF] [G-Scholar] -
...[Yoo et al., arXiv 2023] What, how, and when should object detectors update in continually changing test domains? [PDF] [G-Scholar] -
...[Jeon et al., arXiv 2023] TTA-DAME: Test-time adaptation with domain augmentation and model ensemble for dynamic driving conditions [PDF] [G-Scholar--] -
MoPL[Gong et al., Misc 2023] Test-time adaptation in 3D object detection using momentum-based pseudo-labeling [PDF] [G-Scholar--] -
MonoTTA[Lin et al., Proc. ECCV 2024] Fully test-time adaptation for monocular 3D object detection [PDF] [G-Scholar] [CODE] -
...[Ruan and Tang, Proc. CVPR Workshops 2024] Fully test-time adaptation for object detection [PDF] [G-Scholar--] [CODE] -
DPO[Chen et al., Proc. ACMMM 2024] Fast online fault diagnosis for PMSM based on adaptation model [PDF] [G-Scholar--] [CODE--] -
MOS[Chen et al., arXiv 2024] MOS: Model synergy for test-time adaptation on LiDAR-based 3D object detection [PDF] [G-Scholar] [CODE--]
-
OIL[Ye et al., Proc. EMNLP Findings 2022] Robust question answering against distribution shifts with test-time adaptation: An empirical study [PDF] [G-Scholar] [CODE] -
CaMeLS[Hu et al., Proc. EMNLP 2023] Meta-learning online adaptation of language models [PDF] [G-Scholar] -
Anti-CF[Su et al., Proc. EMNLP 2023] Beware of model collapse! Fast and stable test-time adaptation for robust question answering [PDF] [G-Scholar--] [CODE] -
MEMO-CL[Singh and Ortega, Proc. AAAI Workshops 2023] Addressing distribution shift at test time in pre-trained language models [PDF] [G-Scholar] -
PCL[Su et al., arXiv 2023] Test-time adaptation with perturbation consistency learning [PDF] [G-Scholar] -
TTem[Wu et al., IEEE SPL 2024] A test-time entropy minimization method for cross-domain linguistic steganalysis [PDF] [G-Scholar] -
STAF[Xiong et al., Proc. LREC-COLING 2024] STAF: Pushing the boundaries of test-time adaptation towards practical noise scenarios [PDF] [G-Scholar--] -
ConDA-TTA[Gu et al., arXiv 2024] Learning domain-invariant features for out-of-context news detection [PDF] [G-Scholar]
-
CEA[Liu et al., arXiv 2023] Advancing test-time adaptation for acoustic foundation models in open-world shifts [PDF] [G-Scholar] -
DSUTA[Lin et al., arXiv 2024] Continual test-time adaptation for end-to-end speech recognition on noisy speech [PDF] [G-Scholar--]
-
Dent[Wang et al., arXiv 2021] Fighting gradients with gradients: Dynamic defenses against adversarial attacks [PDF] [G-Scholar] [CODE] -
PST[Lin et al., arXiv 2024] Improving adversarial robustness for 3D point cloud recognition at test-time through purified self-training [PDF] [G-Scholar--]
-
...[Peirone, Thesis 2022] EGO-T3: Test time training for egocentric videos [PDF] [G-Scholar] -
TeCo[Yi et al., Proc. ICLR 2023] Temporal coherent test-time optimization for robust video classification [PDF] [G-Scholar] -
tt-MCC[Bertrand et al., Proc. NeurIPS 2023] Test-time training for matching-based video object segmentation [PDF] [G-Scholar] -
ConVRT[Cai et al., arXiv 2023] ConVRT: Consistent video restoration through turbulence with test-time optimization of neural video representations [PDF] [G-Scholar] -
...[Ayyoubzadeh., PhD Thesis 2023] Prior-guided deep neural networks for image restoration tasks [PDF] [G-Scholar--] -
DiffTTA[Yang et al., Proc. CVPR 2024] Genuine knowledge from practice: Diffusion test-time adaptation for video adverse weather removal [PDF] [G-Scholar] -
ST2ST[Fahim et al., Proc. CVPR Workshops 2024] ST2ST: Self-supervised test-time adaptation for video action recognition [PDF] [G-Scholar]
-
GAPGC[Chen et al., Proc. ICML Workshops 2022] GraphTTA: Test time adaptation on graph neural networks [PDF] [G-Scholar] -
HomoTTT[Zhang et al., ACM TKDD 2024] A fully test-time training framework for semi-supervised node classification on out-of-distribution graphs [PDF] [G-Scholar]
-
ETLT[Fan et al., arXiv 2022] A simple test-time method for out-of-distribution detection [PDF] [G-Scholar] -
TAAD[Sun et al., arXiv 2024] Continuous test-time domain adaptation for efficient fault detection under evolving operating conditions [PDF] [G-Scholar]
SSA[Adachi et al., Proc. CVPR Workshops 2024] Test-time adaptation for regression by subspace alignment [PDF] [G-Scholar--]
AdaGPAR[Li et al., Machine Intelligence Research 2024] AdaGPAR: Generalizable pedestrian attribute recognition via test-time adaptation [PDF] [G-Scholar--]
-
TabLog[Li et al., Proc. ICML 2024] TabLog: Test-time adaptation for tabular data using logic rules [PDF] [G-Scholar] [CODE] -
...[Kim et al., Misc 2024] AdapTable: Test-time adaptation for tabular data via shift-aware uncertainty calibrator and label distribution handler [PDF] [G-Scholar]
-
PCoTTA[Jiang et al., Proc. NeurIPS 2024] PCoTTA: Continual test-time adaptation for multi-task point cloud understanding [PDF] [G-Scholar--] [CODE--] -
SVWA[Bahri et al., Proc. WACV 2025] Test-time adaptation in point clouds: Leveraging sampling variation with weight averaging [PDF] [G-Scholar] [CODE--]
-
Ev-TTA[Kim et al., Proc. CVPR 2022] Ev-TTA: Test-time adaptation for event-based object recognition [PDF] [G-Scholar] [CODE] -
ODR[Park and D'Amico, arXiv 2022] Robust multi-task learning and online refinement for spacecraft pose estimation across domain gap [PDF] [G-Scholar] [CODE] -
OAP[Belli et al., Proc. ICIP 2022] Online adaptive personalization for face anti-spoofing [PDF] [G-Scholar] -
TTA-MDE[Li et al., Proc. ICRA 2023] Test-time domain adaptation for monocular depth estimation [PDF] [G-Scholar] -
SETA[Chen et al., Proc. CVPR 2023] Open-world pose transfer via sequential test-time adaption [PDF] [G-Scholar] -
TTA-COPE[Lee et al., Proc. CVPR 2023] TTA-COPE: Test-time adaptation for category-level object pose estimation [PDF] [G-Scholar] -
MSA[Lin et al., Proc. CVPR 2023] System-status-aware adaptive network for online streaming video understanding [PDF] [G-Scholar] -
...[Pan et al., Proc. CVPR 2023] Cloud-device collaborative adaptation to continual changing environments in the real-world [PDF] [G-Scholar] -
...[Kim et al., Proc. ICCV 2023] Calibrating panoramic depth estimation for practical localization and mapping [PDF] [G-Scholar] -
UTT[Huang et al., Proc. ACPR 2023] Uncertainty-guided test-time training for face forgery detection [PDF] [G-Scholar] -
...[Almansoori et al., Proc. Scandinavian Conference on Image Analysis 2023] Anchor-ReID: A test time adaptation for person re-identification [PDF] [G-Scholar] -
...[He., Journal of Intelligent Medicine and Healthcare 2023] ECG heartbeat classification under dataset shift [PDF] [G-Scholar] -
...[Park and D'Amico, arXiv 2023] Online supervised training of spaceborne vision during proximity operations using adaptive kalman filtering [PDF] [G-Scholar] -
...[Wimpff et al., arXiv 2023] Calibration-free online test-time adaptation for electroencephalography motor imagery decoding [PDF] [G-Scholar--] [CODE] -
CD-CCA[Wang et al., arXiv 2023] Cloud-device collaborative learning for multimodal large language models [PDF] [G-Scholar] -
...[Yu et al., Proc. ESEC/FSE 2023] Log parsing with generalization ability under new log types [PDF] [G-Scholar] -
RFRA[Yang et al., Proc. ICLR 2024] Test-time adaption against multi-modal reliability bias [PDF] [G-Scholar] -
TALoS[Jang et al., Proc. NeurIPS 2024] TALoS: Enhancing semantic scene completion via test-time adaptation on the line of sight [PDF] [G-Scholar] [CODE] -
CoLA[Chen et al., Proc. NeurIPS 2024] Cross-device collaborative test-time adaptation [PDF] [G-Scholar--] [CODE--] -
T4P[Park et al., Proc. CVPR 2024] Test-time training of trajectory prediction via masked autoencoder and actor-specific token memory [PDF] [G-Scholar] [CODE--] -
...[Kim et al., Proc. AAAI 2024] When model meets new normals: Test-time adaptation for unsupervised time-series anomaly detection [PDF] [G-Scholar] [CODE] -
HTT[Wang et al., Proc. AAAI 2024] Heterogeneous test-time training for multi-modal person re-identification [PDF] [G-Scholar--] [CODE] -
OFTTA[Wang et al., Proc. IMWUT/ UbiComp 2024] Optimization-free test-time adaptation for cross-person activity recognition [PDF] [G-Scholar] [CODE] -
HTTA[Xian et al., Proc. PRCV 2024] Exploring out-of-distribution scene text recognition for driving scenes with hybrid test-time adaptation [PDF] [G-Scholar--] -
TEMP[Adachi et al., Proc. IJCNN 2024] Test-time similarity modification for person re-identification toward temporal distribution shift [PDF] [G-Scholar] -
...[Duan et al., IJCV 2024] Test-time forgery detection with spatial-frequency prompt learning [PDF] [G-Scholar--] -
SHW[Jiang et al., IEEE TITS 2024] Strong-help-weak: An online multi-task inference learning approach for robust advanced driver assistance systems [PDF] [G-Scholar--] -
TA-6DT[Tian et al., Pattern Recognition 2024] Test-time adaptation for 6D pose tracking [PDF] [G-Scholar] [CODE--] -
FT3A[Mao et al., IEEE Internet of Things Journal 2024] Online seizure prediction via fine-tuning and test-time adaptation [PDF] [G-Scholar] -
...[Guo et al., Biomedical Signal Processing and Control 2024] Test time adaptation for cross-domain sleep stage classification [PDF] [G-Scholar--] -
DtCC[Zhu et al., Advanced Engineering Informatics 2024] Cloud-edge test-time adaptation for cross-domain online machinery fault diagnosis via customized contrastive learning [PDF] [G-Scholar] -
...[Park et al., arXiv 2024] Test-time adaptation for depth completion [PDF] [G-Scholar] -
Latte[Cao et al., arXiv 2024] Reliable spatial-temporal voxels for multi-modal test-time adaptation [PDF] [G-Scholar] -
TAIP[Cui et al., arXiv 2024] Online test-time adaptation for interatomic potentials [PDF] [G-Scholar] -
TTA-rPPG[Huang et al., arXiv 2024] Fully test-time rPPG estimation via synthetic signal-guided feature learning [PDF] [G-Scholar] -
LSCD-TTA[Liang et al., arXiv 2024] Low saturation confidence distribution-based test-time adaptation for cross-domain remote sensing image classification [PDF] [G-Scholar]
-
GTTA-ST[Marsden et al., arXiv 2022] Introducing intermediate domains for effective self-training during test-time [PDF] [G-Scholar] -
Co-UCB[Ye et al., Proc. ACL 2023] Multi-source test-time adaptation as dueling bandits for extractive question answering [PDF] [G-Scholar] -
DSS[Chakrabarty et al., Proc. ICLR Workshops 2023] Domain shift signal for low resource continuous test-time adaptation [PDF] [G-Scholar--] -
DrFRODA[Islam et al., arXiv 2023] Active learning guided federated online adaptation: Applications in medical image segmentation [PDF] [G-Scholar] -
...[Jawaid et al., Proc. IROS 2024] Test-time certifiable self-supervision to bridge the Sim2Real gap in event-based satellite pose estimation [PDF] [G-Scholar] -
AETTA[Lee et al., Proc. CVPR 2024] AETTA: Label-free accuracy estimation for test-time adaptation [PDF] [G-Scholar] [CODE] -
EACP[Kasa et al., arXiv 2024] Adapting conformal prediction to distribution shifts without labels [PDF] [G-Scholar] -
DoSAPP[Singh et al., arXiv 2024] Controlling forgetting with test-time data in continual learning [PDF] [G-Scholar]