30/11/2020

Explaining an image classifier's decisions using generative models

Chirag Agarwal, Anh Nguyen

Keywords:

Abstract Paper Similar Papers

Abstract: Perturbation-based explanation methods often measure the contribution of an input feature to an image classifier's outputs by heuristically removing it via e.g. blurring, adding noise, or graying out, which often produce unrealistic, out-of-samples. Instead, we propose to integrate a generative inpainter into three representative attribution methods to remove an input feature. Our proposed change improved all three methods in (1) generating more plausible counterfactual samples under the true data distribution; (2) being more accurate according to three metrics: object localization, deletion, and saliency metrics; and (3) being more robust to hyperparameter changes. Our findings were consistent across both ImageNet and Places365 datasets and two different pairs of classifiers and inpainters.

The video of this talk cannot be embedded. You can watch it here:
https://accv2020.github.io/miniconf/poster_708.html
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ACCV 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 4:10 
 0
 0
 0
 0
 7:38 
 0
 0
 0
 0
 14:15 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 17:28 
 0
 0
 0
 0
 3:01 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 11:40 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 0:57 
 0
 0
 0
 0
 3:01 
 0
 0
 0
 0
 17:54 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 11:00 
 0
 0
 0
 0
 18:27 
 0
 0
 0
 0
 4:45 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 17:44 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 6:52 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 4:54 
 0
 0
 0
 0
 19:11 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 5:00 
 0
 0
 0
 0
 7:33 
 0
 0
 0
 0
 17:01 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 10:10 
 0
 0
 0
 0
 6:40 
 0
 0
 0
 0
 13:49