T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers
arXiv:2403.04523 · doi:10.1109/ACCESS.2024.3405788
Abstract
The development and adoption of Vision Transformers and other deep-learning architectures for image classification tasks has been rapid. However, the "black box" nature of neural networks is a barrier to adoption in applications where explainability is essential. While some techniques for generating explanations have been proposed, primarily for Convolutional Neural Networks, adapting such techniques to the new paradigm of Vision Transformers is non-trivial. This paper presents T-TAME, Transformer-compatible Trainable Attention Mechanism for Explanations, a general methodology for explaining deep neural networks used in image classification tasks. The proposed architecture and training technique can be easily applied to any convolutional or Vision Transformer-like neural network, using a streamlined training approach. After training, explanation maps can be computed in a single forward pass; these explanation maps are comparable to or outperform the outputs of computationally expensive perturbation-based explainability techniques, achieving SOTA performance. We apply T-TAME to three popular deep learning classifier architectures, VGG-16, ResNet-50, and ViT-B-16, trained on the ImageNet dataset, and we demonstrate improvements over existing state-of-the-art explainability methods. A detailed analysis of the results and an ablation study provide insights into how the T-TAME design choices affect the quality of the generated explanation maps.
Accepted
References in corpus (14)
- Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
- Axiomatic Attribution for Deep Networks
- Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay
- From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
- GridMask Data Augmentation
- Are Transformers More Robust Than CNNs?
- Face Transformer for Recognition
- A Consistent and Efficient Evaluation Strategy for Attribution Methods
- TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networks
- The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus
- Holistically Explainable Vision Transformers
- Missingness Bias in Model Debugging