02/02/2021

Enhanced Regularizers for Attributional Robustness

Anindya Sarkar, Anirban Sarkar, Vineeth N Balasubramanian

Keywords:

Abstract Paper Similar Papers

Abstract: Deep neural networks are the default choice of learning models for computer vision tasks. Extensive work has been carried out in recent years on explaining deep models for vision tasks such as classification. However, recent work has shown that it is possible for these models to produce substantially different attribution maps even when two very similar images are given to the network, raising serious questions about trustworthiness. To address this issue, we propose a robust attribution training strategy to improve attributional robustness of deep neural networks. Our method carefully analyzes the requirements for attributional robustness and introduces two new regularizers that preserve a model's attribution map during attacks. Our method surpasses state-of-the-art attributional robustness methods by a margin of approximately 3% to 9% in terms of attribution robustness measures on several datasets including MNIST, FMNIST, Flower and GTSRB.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949314
(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
 4:59 
 0
 0
 0
 0
 6:49 
 0
 0
 0
 0
 16:15 
 0
 0
 0
 0
 2:55 
 1
 0
 0
 1
 12:23 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 7:04 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 7:19 
 0
 0
 0
 0
 9:00 
 0
 0
 0
 0
 4:55 
 0
 0
 0
 0
 15:35 
 0
 0
 0
 0
 16:26 
 0
 0
 0
 0
 5:06 
 0
 0
 0
 0
 3:58 
 0
 0
 0
 0
 8:22 
 0
 0
 0
 0
 2:58 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 14:07 
 0
 0
 0
 0
 11:13 
 0
 0
 0
 1
 4:31 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 11:33 
 0
 0
 0
 0
 9:56 
 0
 0
 0
 0
 3:37 
 0
 0
 0
 0
 5:27 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 16:31 
 0
 0
 0
 0
 14:47 
 0
 0
 0
 0
 5:46 
 0
 0
 0
 0
 15:02 
 0
 0
 0
 0
 3:10 
 0
 0
 0
 0
 13:40 
 0
 0
 0
 1
 5:01 
 0
 0
 0
 0
 4:52 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 15:40 
 0
 0
 0
 0
 11:28 
 0
 0
 0
 0
 12:23 
 0
 0
 0
 0
 15:17