Smooth Kernels Improve Adversarial Robustness and Perceptually-Aligned Gradients

ICLR 2020 Haohan WangXindi WuSongwei GeZachary C. LiptonEric P. Xing

Recent research has shown that CNNs are often overly sensitive to high-frequency textural patterns. Inspired by the intuition that humans are more sensitive to the lower-frequency (larger-scale) patterns we design a regularization scheme that penalizes large differences between adjacent components within each convolutional kernel... (read more)

PDF Abstract


No code implementations yet. Submit your code now


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.