IGL-DT: Iterative Global-Local Feature Learning with Dual-Teacher Semantic Segmentation Framework under Limited Annotation Scheme
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908377728155648 |
|---|---|
| author | Tran, Dinh Dai Quan Nguyen, Hoang-Thien Nguyen, Thanh-Huy To, Gia-Van Nguyen, Tien-Huy Nguyen, Quan |
| author_facet | Tran, Dinh Dai Quan Nguyen, Hoang-Thien Nguyen, Thanh-Huy To, Gia-Van Nguyen, Tien-Huy Nguyen, Quan |
| contents | Semi-Supervised Semantic Segmentation (SSSS) aims to improve segmentation accuracy by leveraging a small set of labeled images alongside a larger pool of unlabeled data. Recent advances primarily focus on pseudo-labeling, consistency regularization, and co-training strategies. However, existing methods struggle to balance global semantic representation with fine-grained local feature extraction. To address this challenge, we propose a novel tri-branch semi-supervised segmentation framework incorporating a dual-teacher strategy, named IGL-DT. Our approach employs SwinUnet for high-level semantic guidance through Global Context Learning and ResUnet for detailed feature refinement via Local Regional Learning. Additionally, a Discrepancy Learning mechanism mitigates over-reliance on a single teacher, promoting adaptive feature learning. Extensive experiments on benchmark datasets demonstrate that our method outperforms state-of-the-art approaches, achieving superior segmentation performance across various data regimes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09797 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IGL-DT: Iterative Global-Local Feature Learning with Dual-Teacher Semantic Segmentation Framework under Limited Annotation Scheme Tran, Dinh Dai Quan Nguyen, Hoang-Thien Nguyen, Thanh-Huy To, Gia-Van Nguyen, Tien-Huy Nguyen, Quan Computer Vision and Pattern Recognition Artificial Intelligence Semi-Supervised Semantic Segmentation (SSSS) aims to improve segmentation accuracy by leveraging a small set of labeled images alongside a larger pool of unlabeled data. Recent advances primarily focus on pseudo-labeling, consistency regularization, and co-training strategies. However, existing methods struggle to balance global semantic representation with fine-grained local feature extraction. To address this challenge, we propose a novel tri-branch semi-supervised segmentation framework incorporating a dual-teacher strategy, named IGL-DT. Our approach employs SwinUnet for high-level semantic guidance through Global Context Learning and ResUnet for detailed feature refinement via Local Regional Learning. Additionally, a Discrepancy Learning mechanism mitigates over-reliance on a single teacher, promoting adaptive feature learning. Extensive experiments on benchmark datasets demonstrate that our method outperforms state-of-the-art approaches, achieving superior segmentation performance across various data regimes. |
| title | IGL-DT: Iterative Global-Local Feature Learning with Dual-Teacher Semantic Segmentation Framework under Limited Annotation Scheme |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2504.09797 |