U-CAM: Visual Explanation using Uncertainty based Class Activation Maps
This work addresses the need for better interpretability in deep learning, specifically for visual question answering, offering incremental improvements in attention maps and certainty estimates.
The paper tackles the problem of explaining deep learning models by proposing U-CAM, a method that uses uncertainty-based class activation maps to provide visual explanations, achieving state-of-the-art results in correlation with human attention regions for visual question answering.
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.