Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers
About
Unsupervised semantic segmentation aims to discover groupings within and across images that capture object and view-invariance of a category without external supervision. Grouping naturally has levels of granularity, creating ambiguity in unsupervised segmentation. Existing methods avoid this ambiguity and treat it as a factor outside modeling, whereas we embrace it and desire hierarchical grouping consistency for unsupervised segmentation. We approach unsupervised segmentation as a pixel-wise feature learning problem. Our idea is that a good representation shall reveal not just a particular level of grouping, but any level of grouping in a consistent and predictable manner. We enforce spatial consistency of grouping and bootstrap feature learning with co-segmentation among multiple views of the same image, and enforce semantic consistency across the grouping hierarchy with clustering transformers between coarse- and fine-grained features. We deliver the first data-driven unsupervised hierarchical semantic segmentation method called Hierarchical Segment Grouping (HSG). Capturing visual similarity and statistical co-occurrences, HSG also outperforms existing unsupervised segmentation methods by a large margin on five major object- and scene-centric benchmarks. Our code is publicly available at https://github.com/twke18/HSG .
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Semantic segmentation | PASCAL VOC 2012 (test) | mIoU41.9 | 1342 | |
| Semantic segmentation | PASCAL VOC (val) | mIoU41.9 | 338 | |
| Semantic segmentation | Cityscapes-C (val) | mIoU32.5 | 56 | |
| Unsupervised image segmentation | Coco-Stuff (test) | Accuracy57.6 | 26 | |
| Unsupervised image segmentation | Potsdam (test) | Accuracy67.4 | 15 | |
| Semantic segmentation | Cityscapes (val) | mIoU32.5 | 5 | |
| Semantic segmentation | KITTI-STEP (val) | mIoU21.7 | 5 |