Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation
About
Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently. Most leading WSSS methods employ a sophisticated multi-stage training strategy to estimate pseudo-labels as precise as possible, but they suffer from high model complexity. In contrast, there exists another research line that trains a single network with image-level labels in one training cycle. However, such a single-stage strategy often performs poorly because of the compounding effect caused by inaccurate pseudo-label estimation. To address this issue, this paper presents a Self-supervised Low-Rank Network (SLRNet) for single-stage WSSS and SSSS. The SLRNet uses cross-view self-supervision, that is, it simultaneously predicts several complementary attentive LR representations from different views of an image to learn precise pseudo-labels. Specifically, we reformulate the LR representation learning as a collective matrix factorization problem and optimize it jointly with the network learning in an end-to-end manner. The resulting LR representation deprecates noisy information while capturing stable semantics across different views, making it robust to the input variations, thereby reducing overfitting to self-supervision errors. The SLRNet can provide a unified single-stage framework for various label-efficient semantic segmentation settings: 1) WSSS with image-level labeled data, 2) SSSS with a few pixel-level labeled data, and 3) SSSS with a few pixel-level labeled data and many image-level labeled data. Extensive experiments on the Pascal VOC 2012, COCO, and L2ID datasets demonstrate that our SLRNet outperforms both state-of-the-art WSSS and SSSS methods with a variety of different settings, proving its good generalizability and efficacy.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Semantic segmentation | PASCAL VOC 2012 (val) | Mean IoU75.1 | 2040 | |
| Semantic segmentation | PASCAL VOC 2012 (test) | mIoU75.5 | 1342 | |
| Semantic segmentation | PASCAL VOC (val) | mIoU69.3 | 338 | |
| Semantic segmentation | COCO 2014 (val) | mIoU35 | 251 | |
| Weakly supervised semantic segmentation | PASCAL VOC 2012 (test) | mIoU69.4 | 158 | |
| Weakly supervised semantic segmentation | PASCAL VOC 2012 (val) | mIoU69.3 | 154 | |
| Semantic segmentation | COCO (val) | mIoU35 | 135 | |
| Semantic segmentation | PASCAL VOC 2012 (train) | mIoU70.3 | 73 | |
| Semantic segmentation | L2ID (val) | mIoU52.3 | 9 | |
| Semantic segmentation | L2ID (test) | mIoU49.03 | 9 |