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

Add to Chrome

Add to Firefox

Picture for Aditya Chattopadhyay

Aditya Chattopadhyay

Interpretable by Design: Learning Predictors by Composing Interpretable Queries

Jul 03, 2022
Aditya Chattopadhyay, Stewart Slocum, Benjamin D. Haeffele, Rene Vidal, Donald Geman

Figure 1 for Interpretable by Design: Learning Predictors by Composing Interpretable Queries

Figure 2 for Interpretable by Design: Learning Predictors by Composing Interpretable Queries

Figure 3 for Interpretable by Design: Learning Predictors by Composing Interpretable Queries

Figure 4 for Interpretable by Design: Learning Predictors by Composing Interpretable Queries

* 30 pages, 14 figures

Access Paper or Ask Questions

Neural Network Attributions: A Causal Perspective

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

Figure 1 for Neural Network Attributions: A Causal Perspective

Figure 2 for Neural Network Attributions: A Causal Perspective

Figure 3 for Neural Network Attributions: A Causal Perspective

Figure 4 for Neural Network Attributions: A Causal Perspective

* 16 pages, 10 Figures

Access Paper or Ask Questions

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

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

Figure 1 for Grad-CAM++: Generalized Gradient-based Visual Explanations for Deep Convolutional Networks

Figure 2 for Grad-CAM++: Generalized Gradient-based Visual Explanations for Deep Convolutional Networks

Figure 3 for Grad-CAM++: Generalized Gradient-based Visual Explanations for Deep Convolutional Networks

Figure 4 for Grad-CAM++: Generalized Gradient-based Visual Explanations for Deep Convolutional Networks

* 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