Unsupervised Semantic Segmentation
Models that learn to segment each image (i.e. assign a class to every pixel) without seeing the ground truth labels.
( Image credit: SegSort: Segmentation by Discriminative Sorting of Segments )
Papers
Showing 1–10 of 95 papers
All datasetsCOCO-Stuff-27Cityscapes testPASCAL VOC 2012 valPotsdam-3COCO-Stuff-3ImageNet-S-50COCO-Stuff-171COCO-Stuff-81SUIMCOCO-Stuff-15ACDC (Adverse Conditions Dataset with Correspondences)Cityscapes val
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | PASS (+Saliency map) | mIoU (test) | 42.3 | — | Unverified |
| 2 | PASS | mIoU (test) | 32 | — | Unverified |
| 3 | MaskContrast (+Saliency map) | mIoU (test) | 24.2 | — | Unverified |
| 4 | PiCIE (Supervised pretrain) | mIoU (test) | 17.6 | — | Unverified |
| 5 | MDC (Supervised pretrain) | mIoU (test) | 14.3 | — | Unverified |