Measuring the Layer-Wise Impact of Image Shortcuts on Deep Model Features
Track: regular paper (up to 6 pages)
Keywords: shortcuts, deep learning, out-of-distribution, distribution shift, representation learning
TL;DR: We propose a controlled experiments framework for accessing the layer-wise impact of arbitrary shortcut-inducing skews on features of deep models
Abstract: Shortcuts, spurious patterns that perform well only on the training distribution, pose a major challenge to deep network reliability (Geirhos et al., 2020). In this work, we investigate the layer-wise impact of image shortcuts on learned features. First, we propose an experiment design that introduces artificial shortcut-inducing skews during training, enabling a counterfactual analysis of how different layers contribute to shortcut-related accuracy degradation. Next, we use our method to study the effects of a patch-like skew on CNNs trained on CIFAR-10 and CIFAR-100. Our analysis reveals that different types of skews affect networks layers differently: class-universal skews (affecting all instances of a target class) and class-specific skews (affecting only one class) impact deeper layers more than non-universal and non-specific skews, respectively. Additionally, we identify the forgetting of shortcut-free features as a key mechanism behind accuracy drop for our class of skews, indicating the potential role of simplicity bias (Shah et al., 2020) and excessive regularization (Sagawa et al., 2020) in shortcut learning.
Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.
Format: No, the presenting author is unable to, or unlikely to be able to, attend in person.
Funding: No, the presenting author of this submission does *not* fall under ICLR’s funding aims, or has sufficient alternate funding.
Presenter: ~Nikita_Tsoy1
Submission Number: 15
Loading