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

by   Junliang Chen, et al.
Shenzhen University

Recent mainstream weakly-supervised semantic segmentation (WSSS) approaches based on image-level annotations mainly relies on binary image-level classification with limited representation capacity. In this paper, we propose a novel semantic learning based framework for WSSS, named SLAM (Semantic Learning based Activation Map). We firstly design a semantic encoder to learn semantics of each object category and extract category-specific semantic embeddings from an input image. The semantic embeddings of foreground and background are then integrated to a segmentation network to learn the activation map. Four loss functions, i.e, category-foreground, category-background, activation regularization, and consistency loss are proposed to ensure the correctness, completeness, compactness and consistency of the activation map. Experimental results show that our semantic learning based SLAM achieves much better performance than binary image-level classification based approaches, i.e., around 3% mIoU higher than OC-CSE <cit.>, CPN <cit.> on PASCAL VOC dataset. Our SLAM also surpasses AMN <cit.> trained with strong per-pixel constraint and CLIMS <cit.> utilizing extra multi-modal knowledge. Code will be made available.


page 4

page 7

page 9


SemFormer: Semantic Guided Activation Transformer for Weakly Supervised Semantic Segmentation

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

Self-supervised Scale Equivariant Network for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation has attracted much research inte...

Learning structure-aware semantic segmentation with image-level supervision

Compared with expensive pixel-wise annotations, image-level labels make ...

Cross Language Image Matching for Weakly Supervised Semantic Segmentation

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

Movable-Object-Aware Visual SLAM via Weakly Supervised Semantic Segmentation

Moving objects can greatly jeopardize the performance of a visual simult...

Please sign up or login with your details

Forgot password? Click here to reset