02/02/2021

Explainable Models with Consistent Interpretations

Vipin Pillai, Hamed Pirsiavash

Keywords:

Abstract Paper Similar Papers

Abstract: Given the widespread deployment of black box deep neural networks in computer vision applications, the interpretability aspect of these black box systems has recently gained traction. Various methods have been proposed to explain the results of such deep neural networks. However, some recent works have shown that such explanation methods are biased and do not produce consistent interpretations. Hence, rather than introducing a novel explanation method, we learn models that are encouraged to be interpretable given an explanation method. We use Grad-CAM as the explanation algorithm and encourage the network to learn consistent interpretations along with maximizing the log-likelihood of the correct class. We show that our method outperforms the baseline on the pointing game evaluation on ImageNet and MS-COCO datasets respectively. We also introduce new evaluation metrics that penalize the saliency map if it lies outside the ground truth bounding box or segmentation mask, and show that our method outperforms the baseline on these metrics as well. Moreover, our model trained with interpretation consistency generalizes to other explanation algorithms on all the evaluation metrics. The code and models are publicly available.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949002
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 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
 14:14 
 0
 0
 0
 0
 10:12 
 0
 0
 0
 0
 4:43 
 0
 0
 0
 0
 8:43 
 0
 0
 0
 0
 14:06 
 0
 0
 0
 0
 13:28 
 0
 0
 0
 0
 19:54 
 0
 0
 0
 0
 4:53 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 8:51 
 0
 0
 0
 1
 5:00 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 4:55 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 8:26 
 0
 1
 0
 0
 4:59 
 0
 0
 0
 0
 11:48 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 13:32 
 0
 0
 0
 0
 14:34 
 0
 0
 0
 0
 12:05 
 0
 0
 0
 0
 19:59 
 0
 0
 0
 0
 12:54 
 0
 0
 0
 0
 6:50 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 3:27 
 0
 0
 0
 0
 15:17 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 5:15 
 0
 0
 0
 0
 4:42 
 0
 0
 0
 0
 2:58 
 0
 0
 0
 0
 11:58 
 0
 0
 0
 0
 3:59 
 0
 0
 0
 0
 14:21 
 0
 0
 0
 0
 5:16 
 0
 0
 0
 0
 14:37 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 12:11