Semi-Supervised Semantic Segmentation via Marginal Contextual Information
Abstract: We present a novel confidence refinement scheme that enhances pseudo-labels in semi-supervised semantic segmentation. Unlike existing methods, which filter pixels with low-confidence predictions in isolation, our approach leverages the spatial correlation of labels in segmentation maps by grouping neighboring pixels and considering their pseudo-labels collectively. With this contextual information, our method, named S4MC, increases the amount of unlabeled data used during training while maintaining the quality of the pseudo-labels, all with negligible computational overhead. Through extensive experiments on standard benchmarks, we demonstrate that S4MC outperforms existing state-of-the-art semi-supervised learning approaches, offering a promising solution for reducing the cost of acquiring dense annotations. For example, S4MC achieves a 1.39 mIoU improvement over the prior art on PASCAL VOC 12 with 366 annotated images. The code to reproduce our experiments is available at https://s4mcontext.github.io/
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: Improved version with requsets and comments from the reviewers, added $\alpha_t$ formula and fixed typos and mistakes.
Assigned Action Editor: ~Pavel_Tokmakov2
Submission Number: 2434
Loading