Semi-Supervised Semantic Segmentation with High- and Low-level Consistency
This work addresses the challenge of dense pixel-level classification for computer vision tasks, offering improvements in scenarios with very few labeled samples, though it appears incremental as it builds on existing semi-supervised methods.
The paper tackles the problem of semi-supervised semantic segmentation with limited labeled data by proposing a dual-branch approach that reduces low- and high-level artifacts, achieving new state-of-the-art results on benchmarks like PASCAL VOC 2012, PASCAL-Context, and Cityscapes.
The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised setting, dense pixel-level classification with limited data has only drawn attention recently. In this work, we propose an approach for semi-supervised semantic segmentation that learns from limited pixel-wise annotated samples while exploiting additional annotation-free images. It uses two network branches that link semi-supervised classification with semi-supervised segmentation including self-training. The dual-branch approach reduces both the low-level and the high-level artifacts typical when training with few labels. The approach attains significant improvement over existing methods, especially when trained with very few labeled samples. On several standard benchmarks - PASCAL VOC 2012, PASCAL-Context, and Cityscapes - the approach achieves new state-of-the-art in semi-supervised learning.