IGL-DT: Iterative Global-Local Feature Learning with Dual-Teacher Semantic Segmentation Framework under Limited Annotation Scheme
This work addresses a challenge in semi-supervised semantic segmentation for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of balancing global semantic representation with fine-grained local feature extraction in semi-supervised semantic segmentation by proposing IGL-DT, a tri-branch framework with a dual-teacher strategy, which outperforms state-of-the-art methods on benchmark datasets.
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.