Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning Approach


Oct 30, 2021
Anindya Sarkar, Anirban Sarkar, Sowrya Gali, Vineeth N Balasubramanian

* 16 pages, 9 figures, Accepted at NeurIPS 2021, Code at https://github.com/sowgali/Get-Fooled-for-the-Right-Reason 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Inducing Semantic Grouping of Latent Concepts for Explanations: An Ante-Hoc Approach


Aug 25, 2021
Anirban Sarkar, Deepak Vijaykeerthy, Anindya Sarkar, Vineeth N Balasubramanian

* 11 pages, 7 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Enhanced Regularizers for Attributional Robustness


Dec 28, 2020
Anindya Sarkar, Anirban Sarkar, Vineeth N Balasubramanian

* 15 pages, 18 figures, Accepted at AAAI 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Neural Network Attributions: A Causal Perspective


Feb 07, 2019
Aditya Chattopadhyay, Piyushi Manupriya, Anirban Sarkar, Vineeth N Balasubramanian

* 16 pages, 10 Figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Grad-CAM++: Generalized Gradient-based Visual Explanations for Deep Convolutional Networks


May 08, 2018
Aditya Chattopadhyay, Anirban Sarkar, Prantik Howlader, Vineeth N Balasubramanian

* 16 Pages, 10 Figures, 10 Tables. Accepted in the proceedings of IEEE Winter Conf. on Applications of Computer Vision (WACV2018). Extended version is under review at IEEE Transactions on Pattern Analysis and Machine Intelligence 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email