Skip to content

Commit b73d4e3

Browse files
committed
fix: typo
1 parent abb6bfc commit b73d4e3

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

en/cv.html

+1-1
Original file line numberDiff line numberDiff line change
@@ -42,7 +42,7 @@ <h2>PhD Thesis</h2>
4242
<hr>
4343
<div class="phd-description">
4444
<p>
45-
Anomaly detection aims to discover abnormal patterns hidden in multidimensional radar signals and images. This research field is essential in data mining for quickly isolating irregular or suspicious segments in large amounts of the database. Some examples are: Oil Slick, Turbulent ship wake, Levee anomaly, Archeology. Having data from Sentinel 1 satellite, NASA Jet Propulsion Laboratory airborne radar, ALOS-2 satellite, TerraSAR-X satellite, etc., but often come unlabeled, anomaly detection processus relies on unsupervised and semi-supervised learning algorithms. With the rise of self-supervised learning techniques and deep neural networks, pretext features can be vectorized requiring little to no labeled data. The thesis primarily investigates towards guiding the self-supervised learning process to extract representations suitable for anomaly detection. These characteristics cover SAR diversities aspect:
45+
Anomaly detection aims to discover abnormal patterns hidden in multidimensional radar signals and images. This research field is essential in data mining for quickly isolating irregular or suspicious segments in large amounts of the database. Some examples are: Oil Slick, Turbulent ship wake, Levee anomaly, Archaeology. Having data from Sentinel 1 satellite, NASA Jet Propulsion Laboratory airborne radar, ALOS-2 satellite, TerraSAR-X satellite, etc., but often come unlabeled, anomaly detection processus relies on unsupervised and semi-supervised learning algorithms. With the rise of self-supervised learning techniques and deep neural networks, pretext features can be vectorized requiring little to no labeled data. The thesis primarily investigates towards guiding the self-supervised learning process to extract representations suitable for anomaly detection. These characteristics cover SAR diversities aspect:
4646
</p>
4747
<ul>
4848
<li>Polarimetric and Interferometric channels</li>

0 commit comments

Comments
 (0)