Class Activation Map generation by Multiple Level Class Grouping and Orthogonal Constraint
This work addresses a specific issue in weakly supervised learning for computer vision, offering an incremental improvement over existing CAM methods.
The paper tackles the problem of small and local class activation maps (CAM) in weakly supervised tasks by using multiple classification models based on hierarchical clustering of class relationships, along with an orthogonal module and two-branch CAM generation. Experimental results on PASCAL VOC 2012 show improved CAM generation.
Class activation map (CAM) highlights regions of classes based on classification network, which is widely used in weakly supervised tasks. However, it faces the problem that the class activation regions are usually small and local. Although several efforts paid to the second step (the CAM generation step) have partially enhanced the generation, we believe such problem is also caused by the first step (training step), because single classification model trained on the entire classes contains finite discriminate information that limits the object region extraction. To this end, this paper solves CAM generation by using multiple classification models. To form multiple classification networks that carry different discriminative information, we try to capture the semantic relationships between classes to form different semantic levels of classification models. Specifically, hierarchical clustering based on class relationships is used to form hierarchical clustering results, where the clustering levels are treated as semantic levels to form the classification models. Moreover, a new orthogonal module and a two-branch based CAM generation method are proposed to generate class regions that are orthogonal and complementary. We use the PASCAL VOC 2012 dataset to verify the proposed method. Experimental results show that our approach improves the CAM generation.