Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation

11/22/2022
by   Zesen Cheng, et al.
0

Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted. Although tremendous efforts have been made to recall precise and complete locations for each class, existing methods still commonly suffer from the unsolicited Out-of-Candidate (OC) error predictions that not belongs to the label candidates, which could be avoidable since the contradiction with image-level class tags is easy to be detected. In this paper, we develop a group ranking-based Out-of-Candidate Rectification (OCR) mechanism in a plug-and-play fashion. Firstly, we adaptively split the semantic categories into In-Candidate (IC) and OC groups for each OC pixel according to their prior annotation correlation and posterior prediction correlation. Then, we derive a differentiable rectification loss to force OC pixels to shift to the IC group. Incorporating our OCR with seminal baselines (e.g., AffinityNet, SEAM, MCTformer), we can achieve remarkable performance gains on both Pascal VOC (+3.2 negligible extra training overhead, which justifies the effectiveness and generality of our OCR.

READ FULL TEXT

page 1

page 2

page 4

page 8

page 12

page 13

page 15

research
03/02/2022

Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation

Extracting class activation maps (CAM) is arguably the most standard ste...
research
05/02/2023

Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation with weak labels is a long-lived...
research
05/09/2023

Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation

Weakly Supervised Semantic Segmentation (WSSS) with only image-level sup...
research
04/15/2021

Learning structure-aware semantic segmentation with image-level supervision

Compared with expensive pixel-wise annotations, image-level labels make ...
research
10/14/2021

Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast

Though image-level weakly supervised semantic segmentation (WSSS) has ac...
research
12/16/2021

Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation

Image-level weakly supervised semantic segmentation (WSSS) is a fundamen...
research
03/30/2022

Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds

Weakly-supervised semantic segmentation (WSSS) has recently gained much ...

Please sign up or login with your details

Forgot password? Click here to reset