Fetching the paper…

Reading the bibliography…

2016

Grad-CAM: Why did you say that?

Selvaraju, Ramprasaath R, Das, Abhishek, Vedantam, Ramakrishna et al.

Original
PDF
Post on X

Understand

We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual explanations.

Our approach, called Gradient-weighted Class Activation Mapping (Grad-CAM), uses class-specific gradient information to localize important regions.
These localizations are combined with existing pixel-space visualizations to create a novel high-resolution and class-discriminative visualization called Guided Grad-CAM.
These methods help better understand CNN-based models, including image captioning and visual question answering (VQA) models.

Grad-CAM: Why did you say that? · Around

Built on

ImageNet: A Large-Scale Hierarchical Image Database
J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei · 2009
Earlier work this paper cites.
HOGgles: Visualizing Object Detection Features
C. Vondrick, A. Khosla, T. Malisiewicz, and A. Torralba · 2013
Earlier work this paper cites.
Striving for Simplicity: The All Convolutional Net
Original
J. T. Springenberg, A. Dosovitskiy, T. Brox, and M. A. Riedmiller · 2014
Earlier work this paper cites.
Visualizing and understanding convolutional networks
M. D. Zeiler and R. Fergus · 2014
Earlier work this paper cites.

Similar

CloudCV: Large Scale Distributed Computer Vision as a Cloud Service
H. Agrawal, C. S. Mathialagan, Y. Goyal, N. Chavali, P. Banik, A. Mohapatra, A. Osman, and D. Batra · 2015
Cited alongside, same era.
Deep visual-semantic alignments for generating image descriptions
A. Karpathy and L. Fei-Fei · 2015
Cited alongside, same era.
Deeper LSTM and normalized CNN Visual Question Answering model
J. Lu, X. Lin, D. Batra, and D. Parikh · 2015
Cited alongside, same era.
DenseCap: Fully Convolutional Localization Networks for Dense Captioning
J. Johnson, A. Karpathy, and L. Fei-Fei · 2016
Cited alongside, same era.

Then

Hierarchical question-image co-attention for visual question answering
J. Lu, J. Yang, D. Batra, and D. Parikh · 2016
Closest in time.
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
M. T. Ribeiro, S. Singh, and C. Guestrin · 2016
Closest in time.
Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization
Original
R. Selvaraju, A. Das, R. Vedantam, M. Cogswell, D. Parikh, and D. Batra · 2016
Closest in time.
Learning Deep Features for Discriminative Localization
Original
B. Zhou, A. Khosla, L. A., A. Oliva, and A. Torralba · 2016
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…