Abstract
Existing saliency-guided training approaches improve model generalization by incorporating a loss term that compares the model's class activation map (CAM) for a sample's true-class ({\it i.e.}, correct-label class) against a human reference saliency map. However, prior work has ignored the false-class CAM(s), that is the model's saliency obtained for incorrect-label class. We hypothesize that in binary tasks the true and false CAMs should diverge on the important classification features identified by humans (and reflected in human saliency maps). We use this hypothesis to motivate three new saliency-guided training methods incorporating both true- and false-class model's CAM into the training strategy and a novel post-hoc tool for identifying important features. We evaluate all introduced methods on several diverse binary close-set and open-set classification tasks, including synthetic face detection, biometric presentation attack detection, and classification of anomalies in chest X-ray scans, and find that the proposed methods improve generalization capabilities of deep learning models over traditional (true-class CAM only) saliency-guided training approaches. We offer source codes and model weights\footnote{GitHub repository link removed to preserve anonymity} to support reproducible research.
Abstract (translated)
现有的基于注意力引导的训练方法通过引入一个损失项来改进模型泛化能力，该损失项将模型对样本真实类别的类别激活图（CAM）与人类参考注意力图进行比较。然而，先前的工作忽略了错误类别（即错误标签类别）的CAM。我们假设在二元任务中，真类别和假类别的CAM应该在人类认为重要的分类特征上有所区分（这些特征体现在人类的注意力图中）。基于这一假设，我们提出了三种新的基于注意力引导训练方法，将模型的真类别和假类别的CAM同时纳入训练策略，并提出了一种新颖的事后工具来识别重要特征。我们在多个不同的二元闭集和开集分类任务上评估了所有引入的方法，包括合成人脸检测、生物计量攻击呈现检测以及胸部X光片异常分类，发现所提出的这些方法相比传统的仅基于真类别CAM的注意力引导训练方法能够提高深度学习模型的泛化能力。为了支持可重复研究，我们提供了源代码和模型权重\footnote{GitHub仓库链接已移除以保证匿名性}。
URL
https://arxiv.org/abs/2507.17000
