no code implementations • 25 Sep 2023 • Klara Janouskova, Tamir Shor, Chaim Baskin, Jiri Matas
Test-Time Adaptation (TTA) methods improve the robustness of deep neural networks to domain shift on a variety of tasks such as image classification or segmentation.
no code implementations • 22 Sep 2022 • Klara Janouskova, Mattia Rigotti, Ioana Giurgiu, Cristiano Malossi
These are used within an assisted labeling framework where the annotators can interact with them as proposal segmentation masks by deciding to accept, reject or modify them, and interactions are logged as weak labels to further refine the classifier.