<ul><li>Image classification models trained on clean data often suffer from significant performance degradation when exposed to testing corrupted data, such as images with impulse noise, Gaussian noise, or environmental noise.</li><li>Robust learning algorithms like Sharpness-Aware Minimization (SAM) have shown promise in improving overall model robustness and generalization, but they fall short in addressing biased performance degradation across demographic subgroups.</li><li>FairSAM introduces a novel metric to assess performance degradation across subgroups under data corruption and integrates fairness-oriented strategies into SAM.</li><li>Experiments demonstrate that FairSAM reconciles robustness and fairness, offering a structured solution for equitable and resilient image classification in the presence of data corruption.</li></ul>

FairSAM: Fair Classification on Corrupted Data Through Sharpness-Aware Minimization

Discover more