A new unsupervised instance segmentation framework using MultiCut on self-supervised features, a superpixel-guided mask loss, and adaptive self-training reports SOTA results on COCO, VOC, UVO, KITTI, and SSDD.
Superpixels and polygons using sim- ple non-iterative clustering, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Unsupervised Instance Segmentation with Superpixels
A new unsupervised instance segmentation framework using MultiCut on self-supervised features, a superpixel-guided mask loss, and adaptive self-training reports SOTA results on COCO, VOC, UVO, KITTI, and SSDD.