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

## TL;DR

This paper introduces U-CAM, a method that combines uncertainty estimation with class activation maps to improve visual explanations and model confidence in visual question answering tasks.

## Contribution

The paper presents a novel approach integrating probabilistic deep learning with gradient-based attention maps to enhance explanation quality and certainty estimation.

## Key findings

- Improved certainty estimates correlate better with misclassified samples.
- State-of-the-art attention maps align more closely with human attention regions.
- Enhanced explanations lead to consistent performance improvements in visual question answering.

## Abstract

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.