Localizing Common Objects Using Common Component Activation Map.

Weihao Li, Omid Hosseini Jafari, Carsten Rother

Abstract: In this work, we propose an approach to localize common objects from novel object categories in a set of images. We solve this problem using a new common component activation map (CCAM) in which we treat the class-specific activation maps (CAM) as components to discover the com- mon components in the image set. We show that our approach can generalize on novel object categories in our experiments.