Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation

by   Jinheng Xie, et al.
Shenzhen University

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^2AM) 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^2AM 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^2AM.


page 1

page 3

page 6

page 8


Cross Language Image Matching for Weakly Supervised Semantic Segmentation

It has been widely known that CAM (Class Activation Map) usually only ac...

Weakly Supervised Semantic Segmentation using Out-of-Distribution Data

Weakly supervised semantic segmentation (WSSS) methods are often built o...

Open-World Weakly-Supervised Object Localization

While remarkable success has been achieved in weakly-supervised object l...

Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation

This paper studies the problem of learning semantic segmentation from im...

SLAM: Semantic Learning based Activation Map for Weakly Supervised Semantic Segmentation

Recent mainstream weakly-supervised semantic segmentation (WSSS) approac...

Mitigating Biased Activation in Weakly-supervised Object Localization via Counterfactual Learning

In this paper, we focus on an under-explored issue of biased activation ...

Extracting Class Activation Maps from Non-Discriminative Features as well

Extracting class activation maps (CAM) from a classification model often...

Please sign up or login with your details

Forgot password? Click here to reset