Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915211196235776 |
|---|---|
| author | Yin, Jianjian Chen, Tao Pei, Gensheng Yao, Yazhou Nie, Liqiang Hua, Xiansheng |
| author_facet | Yin, Jianjian Chen, Tao Pei, Gensheng Yao, Yazhou Nie, Liqiang Hua, Xiansheng |
| contents | Consistency regularization has prevailed in semi-supervised semantic segmentation and achieved promising performance. However, existing methods typically concentrate on enhancing the Image-augmentation based Prediction consistency and optimizing the segmentation network as a whole, resulting in insufficient utilization of potential supervisory information. In this paper, we propose a Multi-Constraint Consistency Learning (MCCL) approach to facilitate the staged enhancement of the encoder and decoder. Specifically, we first design a feature knowledge alignment (FKA) strategy to promote the feature consistency learning of the encoder from image-augmentation. Our FKA encourages the encoder to derive consistent features for strongly and weakly augmented views from the perspectives of point-to-point alignment and prototype-based intra-class compactness. Moreover, we propose a self-adaptive intervention (SAI) module to increase the discrepancy of aligned intermediate feature representations, promoting Feature-perturbation based Prediction consistency learning. Self-adaptive feature masking and noise injection are designed in an instance-specific manner to perturb the features for robust learning of the decoder. Experimental results on Pascal VOC2012 and Cityscapes datasets demonstrate that our proposed MCCL achieves new state-of-the-art performance. The source code and models are made available at https://github.com/NUST-Machine-Intelligence-Laboratory/MCCL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17914 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning Yin, Jianjian Chen, Tao Pei, Gensheng Yao, Yazhou Nie, Liqiang Hua, Xiansheng Multimedia Computer Vision and Pattern Recognition Consistency regularization has prevailed in semi-supervised semantic segmentation and achieved promising performance. However, existing methods typically concentrate on enhancing the Image-augmentation based Prediction consistency and optimizing the segmentation network as a whole, resulting in insufficient utilization of potential supervisory information. In this paper, we propose a Multi-Constraint Consistency Learning (MCCL) approach to facilitate the staged enhancement of the encoder and decoder. Specifically, we first design a feature knowledge alignment (FKA) strategy to promote the feature consistency learning of the encoder from image-augmentation. Our FKA encourages the encoder to derive consistent features for strongly and weakly augmented views from the perspectives of point-to-point alignment and prototype-based intra-class compactness. Moreover, we propose a self-adaptive intervention (SAI) module to increase the discrepancy of aligned intermediate feature representations, promoting Feature-perturbation based Prediction consistency learning. Self-adaptive feature masking and noise injection are designed in an instance-specific manner to perturb the features for robust learning of the decoder. Experimental results on Pascal VOC2012 and Cityscapes datasets demonstrate that our proposed MCCL achieves new state-of-the-art performance. The source code and models are made available at https://github.com/NUST-Machine-Intelligence-Laboratory/MCCL. |
| title | Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning |
| topic | Multimedia Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.17914 |