MIRST-DM: Multi-Instance RST with Drop-Max Layer for Robust Classification of Breast Cancer. (arXiv:2205.01674v1 [eess.IV])

Web: http://arxiv.org/abs/2205.01674

Robust self-training (RST) can augment the adversarial robustness of image
classification models without significantly sacrificing models'
generalizability. However, RST and other state-of-the-art defense approaches
failed to preserve the generalizability and reproduce their good adversarial
robustness on small medical image sets. In this work, we propose the
Multi-instance RST with a drop-max layer, namely MIRST-DM, which involves a
sequence of iteratively generated adversarial instances during training to
learn smoother decision boundaries on small datasets. The proposed drop-max
layer eliminates unstable features …

arxiv cancer classification