U-CAM: Visual Explanation using Uncertainty based Class Activation Maps

08/17/2019
by   Badri N. Patro, et al.
8

Understanding and explaining deep learning models is an imperative task. Towards this, we propose a method that obtains gradient-based certainty estimates that also provide visual attention maps. Particularly, we solve for visual question answering task. We incorporate modern probabilistic deep learning methods that we further improve by using the gradients for these estimates. These have two-fold benefits: a) improvement in obtaining the certainty estimates that correlate better with misclassified samples and b) improved attention maps that provide state-of-the-art results in terms of correlation with human attention regions. The improved attention maps result in consistent improvement for various methods for visual question answering. Therefore, the proposed technique can be thought of as a recipe for obtaining improved certainty estimates and explanation for deep learning models. We provide detailed empirical analysis for the visual question answering task on all standard benchmarks and comparison with state of the art methods.

READ FULL TEXT

page 1

page 2

page 8

research
11/19/2019

Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA

In this paper, we aim to obtain improved attention for a visual question...
research
05/10/2017

Survey of Visual Question Answering: Datasets and Techniques

Visual question answering (or VQA) is a new and exciting problem that co...
research
04/10/2019

Advances in Natural Language Question Answering: A Review

Question Answering has recently received high attention from artificial ...
research
01/15/2020

Extending Class Activation Mapping Using Gaussian Receptive Field

This paper addresses the visualization task of deep learning models. To ...
research
04/01/2018

Differential Attention for Visual Question Answering

In this paper we aim to answer questions based on images when provided w...
research
05/14/2018

Did the Model Understand the Question?

We analyze state-of-the-art deep learning models for three tasks: questi...
research
09/02/2021

GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps

We present Gradient Activation Maps (GAM) - a machinery for explaining p...

Please sign up or login with your details

Forgot password? Click here to reset