TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networks

Abstract

The apparent ``black box'' nature of neural networks is a barrier to adoption in applications where explainability is essential. This paper presents TAME (Trainable Attention Mechanism for Explanations), a method for generating explanation maps with a multi-branch hierarchical attention mechanism. TAME combines a target model's feature maps from multiple layers using an attention mechanism, transforming them into an explanation map. TAME can easily be applied to any convolutional neural network (CNN) by streamlining the optimization of the attention mechanism's training method and the selection of target model's feature maps. After training, explanation maps can be computed in a single forward pass. We apply TAME to two widely used models, i.e. VGG-16 and ResNet-50, trained on ImageNet and show improvements over previous top-performing methods. We also provide a comprehensive ablation study comparing the performance of different variations of TAME's architecture. TAME source code is made publicly available at https://github.com/bmezaris/TAME

arXiv commentAccepted for publication in the proceedings of IEEE Int. Symposium on Multimedia (ISM), Naples, Italy, Dec. 2022

References in corpus (4)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay

Cited by in corpus (2)

• T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers
• P-TAME: Explain Any Image Classifier with Trained Perturbations