SOTAVerified

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 110 of 95 papers

TitleStatusHype
Urban1960SatSeg: Unsupervised Semantic Segmentation of Mid-20^th century Urban Landscapes with Satellite ImageriesCode2
LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point CloudsCode1
Federated Unsupervised Semantic Segmentation0
Hierarchical Context Learning of object components for unsupervised semantic segmentationCode0
Scene-Centric Unsupervised Panoptic SegmentationCode2
COIN: Confidence Score-Guided Distillation for Annotation-Free Cell SegmentationCode0
NPSim: Nighttime Photorealistic Simulation From Daytime Images With Monocular Inverse Rendering and Ray Tracing0
GraPix: Exploring Graph Modularity Optimization for Unsupervised Pixel ClusteringCode0
ULTra: Unveiling Latent Token Interpretability in Transformer Based Understanding0
Unsupervised semantic segmentation of urban high-density multispectral point clouds0
Show:102550
← PrevPage 1 of 10Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PriMaPs-EM+HP (DINO ViT-B/8)Accuracy83.3Unverified
2EAGLE (DINO, ViT-B/8)Accuracy83.3Unverified
3HPAccuracy82.4Unverified
4EQUSSAccuracy82Unverified
5PriMaPs-EM (DINO ViT-B/8)Accuracy80.5Unverified
6STEGOAccuracy77Unverified
7InfoSegPixel Accuracy71.6Unverified
8IICAccuracy45.4Unverified