Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging
Qualitative and mechanistic analyses indicate that explanation degradation is primarily associated with the collapse of class-discriminative gradients rather than the disappearance of feature activations, suggesting that model compression should be evaluated beyond aggregate performance.
N. Khalid, Tausifa Jan Saleem, Amal Saqib et al.
· 0 citations