Improving robustness against common corruptions with frequency biased models

IEEE International Conference on Computer Vision (ICCV), 2021
Abstract: CNNs perform remarkably well when the training and test distributions are i.i.d, but unseen image corruptions can cause a surprisingly large drop in performance. In various real scenarios, unexpected distortions, such as random noise, compression artefacts or weather distortions are common phenomena. Improving performance on corrupted images must not result in degraded i.i.d performance - a challenge faced by many state-of-the-art robust approaches. Image corruption types have different characteristics in the frequency spectrum and would benefit from a targeted type of data augmentation, which, however, is often unknown during training. In this paper, we introduce a mixture of two expert models specializing in high and low-frequency robustness, respectively. Moreover, we propose a new regularization scheme that minimizes the total variation (TV) of convolution feature-maps to increase high-frequency robustness. The approach improves on corrupted images without degrading in-distribution performance. We demonstrate this on ImageNet-C and also for real-world corruptions on an automotive dataset, both for object classification and object detection.

Other associated files : paper.pdf [2.7MB]  

Images and movies


BibTex reference

  author       = "T. Saikia and C. Schmid and T.Brox",
  title        = "Improving robustness against common corruptions with frequency biased models",
  booktitle    = "IEEE International Conference on Computer Vision (ICCV)",
  month        = " ",
  year         = "2021",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2021/SB21b"

Other publications in the database