Semi-Supervised Semantic Segmentation via Marginal Contextual Information
This work addresses the high cost of dense annotations for computer vision researchers and practitioners, offering an incremental improvement over existing methods.
The paper tackles the problem of reducing annotation costs in semi-supervised semantic segmentation by introducing a confidence refinement scheme that leverages spatial context to improve pseudo labels, resulting in a 1.39 mIoU improvement over prior art on PASCAL VOC 12 with 366 annotated images.
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/