Search Results for author:
Found 2 papers, 2 papers with code
Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
To mitigate it, TTA methods have utilized the model output's entropy as a confidence metric that aims to determine which samples have a lower likelihood of causing error.
DAFA: Distance-Aware Fair Adversarial Training
The disparity in accuracy between classes in standard training is amplified during adversarial training, a phenomenon termed the robust fairness problem.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
