特征激活图：面向图像分类的深度学习模型可视化解释
Feature Activation Map: Visual Explanation of Deep Learning Models for Image Classification
AI总结：
针对无全连接层的图像分类模型，本文提出事后可视化解释方法FAM，利用图像嵌入相似度计算通道权重并生成解释图，实验验证其有效性。
摘要：
卷积神经网络（CNN）作出的决策可以通过在图像上可视化判别区域来理解和解释。为此，基于类激活图（Class Activation Map，CAM）的方法被提出，作为强大的解释工具，使深度学习模型的预测更具可解释性、透明性和可信度。然而，所有基于CAM的方法（例如CAM、Grad-CAM和Relevance-CAM）都只能用于解释以全连接（FC）层作为分类器的CNN模型。值得注意的是，许多深度学习模型在没有FC层的情况下进行图像分类，例如小样本学习图像分类、对比学习图像分类和图像检索任务。本文提出了一种名为特征激活图（feature activation map，FAM）的事后解释工具，它可以解释不使用FC层作为分类器的深度学习模型。在所提出的FAM算法中，逐通道贡献权重由两个图像嵌入之间的相似度分数推导得到。激活图与相应的归一化贡献权重进行线性组合，形成用于可视化的解释图。在十个用于小样本图像分类、对比学习图像分类和图像检索任务的深度学习模型上进行的定量和定性实验，证明了所提出FAM算法的有效性。
英文摘要：
Decisions made by convolutional neural networks(CNN) can be understood and explained by visualizing discriminative regions on images. To this end, Class Activation Map (CAM) based methods were proposed as powerful interpretation tools, making the prediction of deep learning models more explainable, transparent, and trustworthy. However, all the CAM-based methods (e.g., CAM, Grad-CAM, and Relevance-CAM) can only be used for interpreting CNN models with fully-connected (FC) layers as a classifier. It is worth noting that many deep learning models classify images without FC layers, e.g., few-shot learning image classification, contrastive learning image classification, and image retrieval tasks. In this work, a post-hoc interpretation tool named feature activation map (FAM) is proposed, which can interpret deep learning models without FC layers as a classifier. In the proposed FAM algorithm, the channel-wise contribution weights are derived from the similarity scores between two image embeddings. The activation maps are linearly combined with the corresponding normalized contribution weights, forming the explanation map for visualization. The quantitative and qualitative experiments conducted on ten deep learning models for few-shot image classification, contrastive learning image classification and image retrieval tasks demonstrate the effectiveness of the proposed FAM algorithm.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
