Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Ngnawé, Jonas"'
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 imperceptible perturbations, creating serious risks when deploying them fo
Externí odkaz:
http://arxiv.org/abs/2406.18451
Autor:
Sahoo, Sabyasachi, ElAraby, Mostafa, Ngnawe, Jonas, Pequignot, Yann, Precioso, Frederic, Gagne, Christian
Test Time Adaptation (TTA) addresses the problem of distribution shift by enabling pretrained models to learn new features on an unseen domain at test time. However, it poses a significant challenge to maintain a balance between learning new features
Externí odkaz:
http://arxiv.org/abs/2404.03784
Deep networks have achieved impressive results on a range of well-curated benchmark datasets. Surprisingly, their performance remains sensitive to perturbations that have little effect on human performance. In this work, we propose a novel extension
Externí odkaz:
http://arxiv.org/abs/2304.02847