activity
20242026
collaborators

5 papers

cs.LG2026

Reliability-Gated Source Anchoring for Continual Test-Time Adaptation

Vikash Singh, Debargha Ganguly, Weicong Chen +8

Continual test-time adaptation (CTTA) updates a pretrained model online on an unlabeled, non-stationary stream while anchoring it to a frozen source checkpoint. This anchor is usef…

cs.LG2026

Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling

Jonas Ngnawé, Maxime Heuillet, Sabyasachi Sahoo +5

Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims to simultaneously achieve adaptation to…

cs.CV2025

GROOD: GRadient-Aware Out-of-Distribution Detection

Mostafa ElAraby, Sabyasachi Sahoo, Yann Pequignot +2

Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models in real-world applications. Existing methods typically focus on feature represen…

cs.LG2025

A Layer Selection Approach to Test Time Adaptation

Sabyasachi Sahoo, Mostafa ElAraby, Jonas Ngnawe +3

Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When faced with challenging shifts, most met…

cs.LG2024

Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers

Jonas Ngnawé, Sabyasachi Sahoo, Yann Pequignot +2

Despite extensive research on adversarial training strategies to improve robustness, the decisions of even the most robust deep learning models can still be quite sensitive to impe…