.png){kind=icon}
Return
A multi-strategy contrastive learning framework for weakly supervised semantic segmentation
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2022.109298.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Weakly supervised semantic segmentation (WSSS) has gained significant popularity as it relies only on weak labels such as image level annotations rather than the pixel level annotations required by super-vised semantic segmentation (SSS) methods. Despite drastically reduced annotation costs, typical feature representations learned from WSSS are only representative of some salient parts of objects and less re-liable compared to SSS due to the weak guidance during training. In this paper, we propose a novel Multi-Strategy Contrastive Learning (MuSCLe) framework to obtain enhanced feature representations and improve WSSS performance by exploiting similarity and dissimilarity of contrastive sample pairs at im-age, region, pixel and object boundary levels. Extensive experiments demonstrate the effectiveness of our method and show that MuSCLe outperforms current state-of-the-art methods on the widely used PASCAL VOC 2012 dataset.(c) 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )
Keywords:
Weakly supervised learning
Representation learning
Contrastive learning
Semantic segmentation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
View more organizations
Cited Papers
Learning pseudo labels for semi-and-weakly supervised semantic segmentation.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveBoundarymix: Generating pseudo-training images for improving segmentation with scribble annotationsPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveEnd-to-end weakly supervised semantic segmentation with reliable region miningPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveVideo semantic segmentation via feature propagation with holistic attentionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveWeakly-supervised semantic segmentation with saliency and incremental supervision updatingPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSave no more