papers AI Learner
The Github is limit! Click to go to the new site.

Grad-CAM: Why did you say that?

2017-01-25
Ramprasaath R Selvaraju, Abhishek Das, Ramakrishna Vedantam, Michael Cogswell, Devi Parikh, Dhruv Batra

Abstract

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. We evaluate our visual explanations by measuring their ability to discriminate between classes, to inspire trust in humans, and their correlation with occlusion maps. Grad-CAM provides a new way to understand CNN-based models. We have released code, an online demo hosted on CloudCV, and a full version of this extended abstract.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1611.07450

PDF

https://arxiv.org/pdf/1611.07450


Similar Posts

Comments