English

Anomalous behaviour in loss-gradient based interpretability methods

Machine Learning 2022-07-19 v1 Artificial Intelligence Information Retrieval

Abstract

Loss-gradients are used to interpret the decision making process of deep learning models. In this work, we evaluate loss-gradient based attribution methods by occluding parts of the input and comparing the performance of the occluded input to the original input. We observe that the occluded input has better performance than the original across the test dataset under certain conditions. Similar behaviour is observed in sound and image recognition tasks. We explore different loss-gradient attribution methods, occlusion levels and replacement values to explain the phenomenon of performance improvement under occlusion.

Keywords

Cite

@article{arxiv.2207.07769,
  title  = {Anomalous behaviour in loss-gradient based interpretability methods},
  author = {Vinod Subramanian and Siddharth Gururani and Emmanouil Benetos and Mark Sandler},
  journal= {arXiv preprint arXiv:2207.07769},
  year   = {2022}
}

Comments

Accepted at ICLR RobustML workshop 2021

R2 v1 2026-06-25T00:57:48.718Z