Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation
Preprint
Abstract
While class activation map (CAM) generated by image classification network has been widely used for weakly supervised object localization (WSOL) and semantic segmentation (WSSS), such classifiers usually focus on discriminative object regions. In this paper, we propose Contrastive learning for Class-agnostic Activation Map (C$^2$AM) generation only using unlabeled image data, without the involvement of image-level supervision. The core idea comes from the observation that i) semantic information of foreground objects usually differs from their backgrounds; ii) foreground objects with similar appearance or background with similar color/texture have similar representations in the feature space. We form the positive and negative pairs based on the above relations and force the network to disentangle foreground and background with a class-agnostic activation map using a novel contrastive loss. As the network is guided to discriminate cross-image foreground-background, the class-agnostic activation maps learned by our approach generate more complete object regions. We successfully extracted from C$^2$AM class-agnostic object bounding boxes for object localization and background cues to refine CAM generated by classification network for semantic segmentation. Extensive experiments on CUB-200-2011, ImageNet-1K, and PASCAL VOC2012 datasets show that both WSOL and WSSS can benefit from the proposed C$^2$AM.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- Geometry Constrained Weakly Supervised Object Localization2020
- Inter-Image Communication for Weakly Supervised Localization2020
- Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation2020
- Unsupervised object discovery and co-localization by deep descriptor transformationPattern Recognition, 2019
- Self-produced Guidance for Weakly-Supervised Object Localization2018
- Learning Deep Features for Discriminative Localization2016
- FaceNet: A unified embedding for face recognition and clustering2015
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- Dimensionality Reduction by Learning an Invariant Mapping2006
- Learning a Similarity Metric Discriminatively, with Application to Face Verification2005