Why Do These Match? Explaining the Behavior of Image Similarity Models



  • Bryan A. Plummer
  • Mariya I. Vasileva
  • Vitali Petsiuk
  • Kate Saenko
  • David Forsyth

Published on



Computer Vision ECCV

Explaining a deep learning model can help users understand its behavior and allow researchers to discern its shortcomings. Recent work has primarily focused on explaining models for tasks like image classification or visual question answering. In this paper, we introduce Salient Attributes for Network Explanation (SANE) to explain image similarity models, where a model’s output is a score measuring the similarity of two inputs rather than a classification score. In this task, an explanation depends on both of the input images, so standard methods do not apply. Our SANE explanations pairs a saliency map identifying important image regions with an attribute that best explains the match. We find that our explanations provide additional information not typically captured by saliency maps alone, and can also improve performance on the classic task of attribute recognition. Our approach’s ability to generalize is demonstrated on two datasets from diverse domains, Polyvore Outfits and Animals with Attributes 2.

This paper has been published at ECCV 2020.

Please cite our work using the BibTeX below.

     author={Bryan A. Plummer and Mariya I. Vasileva and Vitali Petsiuk and Kate Saenko and David Forsyth},
     title={Why do These Match? Explaining the Behavior of Image Similarity Models},
     booktitle = {The European Conference on Computer Vision (ECCV)},
     year = {2020}
Close Modal