用可训练扰动解释任意图像分类器，高效且无需修改原模型
P-TAME: Explain Any Image Classifier with Trained Perturbations
- 引入可训练扰动机制，通过辅助分类器提取特征实现通用解释
- 单次前向传播生成高分辨率解释，计算效率远超传统方法
- 适用于VGG-16、ResNet-50、ViT-B-16等主流模型，效果领先
深度神经网络在需要提供决策依据的高风险领域应用受限，因其固有的黑箱特性。本文提出P-TAME（基于扰动的可训练注意力机制解释方法），一种无需依赖目标模型结构的通用图像分类器解释方法。P-TAME使用辅助图像分类器从输入图像中提取特征，避免为不同主干模型定制解释策略。与传统基于扰动的方法相比，P-TAME在推理阶段仅需一次前向传播即可生成高分辨率解释，显著降低计算开销。我们在VGG-16、ResNet-50和ViT-B-16三类广泛使用的图像分类器上验证了该方法，定量与定性结果表明其性能达到或超过现有可解释性方法，包括特定模型的解释方案。代码与训练好的模型将在论文接收后公开。
原文摘要 · Abstract (English)
The adoption of Deep Neural Networks (DNNs) in critical fields where predictions need to be accompanied by justifications is hindered by their inherent black-box nature. In this paper, we introduce P-TAME (Perturbation-based Trainable Attention Mechanism for Explanations), a model-agnostic method for explaining DNN-based image classifiers. P-TAME employs an auxiliary image classifier to extract features from the input image, bypassing the need to tailor the explanation method to the internal architecture of the backbone classifier being explained. Unlike traditional perturbation-based methods, which have high computational requirements, P-TAME offers an efficient alternative by generating high-resolution explanations in a single forward pass during inference. We apply P-TAME to explain the decisions of VGG-16, ResNet-50, and ViT-B-16, three distinct and widely used image classifiers. Quantitative and qualitative results show that our method matches or outperforms previous explainability methods, including model-specific approaches. Code and trained models will be released upon acceptance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。