Biased Binary Attribute Classifiers Ignore the Majority Classes

arXiv:2403.14435v1 Announce Type: cross
Abstract: 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 …

abstract arxiv binary categorical class classification classifiers cs.ai cs.cv cs.lg decisions gradient however mapping paper tasks type work world