Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank
This work addresses the problem of reducing annotation costs for semantic segmentation in computer vision, presenting an incremental improvement over existing methods.
The paper tackles semi-supervised semantic segmentation by introducing a pixel-level contrastive learning module that uses a class-wise memory bank to enforce similarity in feature representations for same-class samples, achieving state-of-the-art results on public benchmarks with larger improvements in low-labeled-data scenarios.
This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach outperforms the current state-of-the-art for semi-supervised semantic segmentation and semi-supervised domain adaptation on well-known public benchmarks, with larger improvements on the most challenging scenarios, i.e., less available labeled data. https://github.com/Shathe/SemiSeg-Contrastive