XRAI: Better Attributions Through Regions

Andrei Kapishnikov, Tolga Bolukbasi, Fernanda Viegas, Michael Terry; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 4948-4957


Saliency methods can aid understanding of deep neural networks. Recent years have witnessed many improvements to saliency methods, as well as new ways for evaluating them. In this paper, we 1) present a novel region-based attribution method, XRAI, that builds upon integrated gradients (Sundararajan et al. 2017), 2) introduce evaluation methods for empirically assessing the quality of image-based saliency maps (Performance Information Curves (PICs)), and 3) contribute an axiom-based sanity check for attribution methods. Through empirical experiments and example results, we show that XRAI produces better results than other saliency methods for common models and the ImageNet dataset.

Related Material

[pdf] [supp]
author = {Kapishnikov, Andrei and Bolukbasi, Tolga and Viegas, Fernanda and Terry, Michael},
title = {XRAI: Better Attributions Through Regions},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}