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
1SGSegClustering [Accuracy]55.7Unverified
2DynaSeg - FSF (ResNet-18 FPN)Clustering [mIoU]54.1Unverified
3SANClustering [Accuracy]52Unverified
4DiffCutClustering [mIoU]49.1Unverified
5PiCIEClustering [Accuracy]48.1Unverified
6HCL (ViT-S/8)Linear Classifier [mIoU]47.4Unverified
7HCL (ViT-S/16)Linear Classifier [mIoU]45.8Unverified
8CAUSE (DINOv2, ViT-B/14)Clustering [mIoU]45.3Unverified
9Ours (SlotCon)Clustering [Accuracy]42.36Unverified
10CAUSE (ViT-B/8)Clustering [mIoU]41.9Unverified