有偏的二元属性分类器忽略了多数类
Biased Binary Attribute Classifiers Ignore the Majority Classes
AI总结：
本文将基于梯度的CAM方法扩展至二元分类器，发现不平衡数据训练的有偏分类器主要依赖偏置激活来预测多数类，而采用类别权重训练的平衡分类器则能对各类别均产生合理的预期激活。
摘要：
为了可视化分类器基于哪些感兴趣区域做出决策，人们开发了不同的类激活映射（CAM）方法。然而，所有这些技术仅针对多类别分类器，尽管大多数现实世界的任务是二元分类。在本文中，我们将基于梯度的CAM技术扩展到二元分类器，并可视化二元面部属性分类器的激活区域。在类别不平衡的数据集上训练不平衡的二元分类器时，众所周知，拥有大量训练样本的多数类比拥有少量训练实例的少数类预测得更好。我们在CelebA数据集上的实验中验证了这些结果，即训练一个不平衡分类器同时提取40个面部属性。人们可能会预期，有偏的分类器已经学会了主要为多数类提取特征，并且激活的成比例能量主要位于图像中属性所在的某些特定区域。然而，我们发现多数类样本的规律激活非常少，而少数类的激活区域似乎大部分是合理的，并与我们的预期重叠。这些结果表明，有偏的分类器主要依赖多数类的偏置激活。通过采用属性特定的类别权重在不平衡数据上训练平衡分类器时，多数类和少数类的分类效果相似，并且几乎所有属性都显示出预期的激活。
英文摘要：
To visualize the regions of interest that classifiers base their decisions on, different Class Activation Mapping (CAM) methods have been developed. However, all of these techniques target categorical classifiers only, though most real-world tasks are binary classification. In this paper, we extend gradient-based CAM techniques to work with binary classifiers and visualize the active regions for binary facial attribute classifiers. When training an unbalanced binary classifier on an imbalanced dataset, it is well-known that the majority class, i.e. the class with many training samples, is mostly predicted much better than minority class with few training instances. In our experiments on the CelebA dataset, we verify these results, when training an unbalanced classifier to extract 40 facial attributes simultaneously. One would expect that the biased classifier has learned to extract features mainly for the majority classes and that the proportional energy of the activations mainly reside in certain specific regions of the image where the attribute is located. However, we find very little regular activation for samples of majority classes, while the active regions for minority classes seem mostly reasonable and overlap with our expectations. These results suggest that biased classifiers mainly rely on bias activation for majority classes. When training a balanced classifier on the imbalanced data by employing attribute-specific class weights, majority and minority classes are classified similarly well and show expected activations for almost all attributes
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。
