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.

翻译：视觉Transformer及其他深度学习架构在图像分类任务中的发展与应用十分迅速。然而，神经网络的"黑箱"特性阻碍了其在可解释性至关重要的应用场景中的推广。尽管已有部分解释生成技术被提出（主要针对卷积神经网络），但将这些技术适配到视觉Transformer的新范式上并非易事。本文提出T-TAME（兼容Transformer的可训练注意力解释机制），这是一种用于解释图像分类任务中深度神经网络的通用方法。所提出的架构与训练技术可通过简化的训练流程，轻松应用于任何卷积或类视觉Transformer神经网络。训练完成后，仅需单次前向传播即可计算解释图；这些解释图可与计算成本高昂的基于扰动的可解释性技术相媲美甚至更优，达到了当前最优性能。我们将T-TAME应用于三种主流深度学习分类架构（在ImageNet数据集上训练的VGG-16、ResNet-50和ViT-B-16），并展示了其对现有最优可解释性方法的改进。通过详尽的结果分析与消融研究，我们揭示了T-TAME设计选择如何影响生成解释图的质量。