{"url":"/sota/unsupervised-semantic-segmentation-on-coco-7","task":{"name":"Unsupervised Semantic Segmentation","url":"/task/unsupervised-semantic-segmentation","note":null},"dataset":{"name":"COCO-Stuff-27","url":"/dataset/coco-stuff"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Models that learn to segment each image (i.e. assign a class to every pixel) without seeing the ground truth labels.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [SegSort: Segmentation by Discriminative Sorting of Segments](http://openaccess.thecvf.com/content_ICCV_2019/papers/Hwang_SegSort_Segmentation_by_Discriminative_Sorting_of_Segments_ICCV_2019_paper.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Clustering [mIoU]","Clustering [Accuracy]","Linear Classifier [mIoU]","Linear Classifier [Accuracy]"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Clustering [mIoU]":null,"Clustering [Accuracy]":"higher","Linear Classifier [mIoU]":null,"Linear Classifier [Accuracy]":"higher"}},"counts":{"rows":29,"rows_with_code":23,"rows_with_paper_page":28,"rows_dated":28,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DynaSeg - FSF (ResNet-18 FPN)","metrics":{"Clustering [Accuracy]":"81.1","Clustering [mIoU]":"54.1"},"uses_additional_data":false,"paper_date":"2024-05-09","paper":"/paper/dynaseg-a-deep-dynamic-fusion-method-for","paper_url":"https://arxiv.org/abs/2405.05477v4","paper_title":"DynaSeg: A Deep Dynamic Fusion Method for Unsupervised Image Segmentation Incorporating Feature Similarity and Spatial Continuity","code":"https://github.com/ryersonmultimedialab/dynaseg","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"DiffCut","metrics":{"Clustering [mIoU]":"49.1"},"uses_additional_data":false,"paper_date":"2024-06-05","paper":"/paper/zero-shot-image-segmentation-via-recursive","paper_url":"https://arxiv.org/abs/2406.02842v2","paper_title":"DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut","code":"https://github.com/paulcouairon/diffcut","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"CAUSE (DINOv2, ViT-B/14)","metrics":{"Clustering [Accuracy]":"78.0","Clustering [mIoU]":"45.3"},"uses_additional_data":false,"paper_date":"2023-10-11","paper":"/paper/causal-unsupervised-semantic-segmentation","paper_url":"https://arxiv.org/abs/2310.07379v1","paper_title":"Causal Unsupervised Semantic Segmentation","code":"https://github.com/ByungKwanLee/Causal-Unsupervised-Segmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"CAUSE (ViT-B/8)","metrics":{"Clustering [Accuracy]":"74.9","Clustering [mIoU]":"41.9"},"uses_additional_data":false,"paper_date":"2023-10-11","paper":"/paper/causal-unsupervised-semantic-segmentation","paper_url":"https://arxiv.org/abs/2310.07379v1","paper_title":"Causal Unsupervised Semantic Segmentation","code":"https://github.com/ByungKwanLee/Causal-Unsupervised-Segmentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"U2Seg","metrics":{"Clustering [Accuracy]":"63.9","Clustering [mIoU]":"30.2"},"uses_additional_data":false,"paper_date":"2023-12-28","paper":"/paper/unsupervised-universal-image-segmentation","paper_url":"https://arxiv.org/abs/2312.17243v1","paper_title":"Unsupervised Universal Image Segmentation","code":"https://github.com/u2seg/u2seg","n_code_links":2,"syntology":{"n_ran":13,"n_unverified":2,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"PriMaPs+STEGO (DINO ViT-B/8)","metrics":{"Clustering [Accuracy]":"57.9","Clustering [mIoU]":"29.7"},"uses_additional_data":false,"paper_date":"2024-04-25","paper":"/paper/boosting-unsupervised-semantic-segmentation","paper_url":"https://arxiv.org/abs/2404.16818v2","paper_title":"Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals","code":"https://github.com/visinf/primaps","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"DepthG (ViT-B/8)","metrics":{"Clustering [Accuracy]":"58.6","Clustering [mIoU]":"29.0","Linear Classifier [Accuracy]":"75.5","Linear Classifier [mIoU]":"41.6"},"uses_additional_data":false,"paper_date":"2023-09-21","paper":"/paper/spatially-guiding-unsupervised-semantic","paper_url":"https://arxiv.org/abs/2309.12378v2","paper_title":"Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling","code":"https://github.com/leonsick/depthg","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"STEGO (ViT-B/8)","metrics":{"Clustering [Accuracy]":"56.9","Clustering [mIoU]":"28.2"},"uses_additional_data":false,"paper_date":"2022-03-16","paper":"/paper/unsupervised-semantic-segmentation-by-2","paper_url":"https://arxiv.org/abs/2203.08414v1","paper_title":"Unsupervised Semantic Segmentation by Distilling Feature Correspondences","code":"https://github.com/mhamilton723/STEGO","n_code_links":3,"syntology":{"n_ran":8,"n_unverified":6,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"EAGLE (DINO, ViT-S/8)","metrics":{"Clustering [Accuracy]":"64.2","Clustering [mIoU]":"27.2","Linear Classifier [Accuracy]":"76.8","Linear Classifier [mIoU]":"43.9"},"uses_additional_data":false,"paper_date":"2024-03-03","paper":"/paper/eagle-eigen-aggregation-learning-for-object","paper_url":"https://arxiv.org/abs/2403.01482v4","paper_title":"EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation","code":"https://github.com/MICV-yonsei/EAGLE","n_code_links":1,"syntology":{"n_ran":14,"n_unverified":5,"n_samples":19,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"SmooSeg (DINO, ViT-S/8)","metrics":{"Clustering [Accuracy]":"63.2","Clustering [mIoU]":"26.7"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"DepthG w/ 3D-LHP (ViT-S/8)","metrics":{"Clustering [Accuracy]":"55.1","Clustering [mIoU]":"26.7","Linear Classifier [Accuracy]":"73.9","Linear Classifier [mIoU]":"37.8"},"uses_additional_data":false,"paper_date":"2023-09-21","paper":"/paper/spatially-guiding-unsupervised-semantic","paper_url":"https://arxiv.org/abs/2309.12378v2","paper_title":"Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling","code":"https://github.com/leonsick/depthg","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"EQUSS","metrics":{"Clustering [Accuracy]":"53.8","Clustering [mIoU]":"25.8","Linear Classifier [Accuracy]":"75.2","Linear Classifier [mIoU]":"41.2"},"uses_additional_data":false,"paper_date":"2023-12-12","paper":"/paper/expand-and-quantize-unsupervised-semantic","paper_url":"https://arxiv.org/abs/2312.07342v1","paper_title":"Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"EQUSS (ViT-S)","metrics":{"Clustering [Accuracy]":"53.8","Clustering [mIoU]":"25.8"},"uses_additional_data":false,"paper_date":"2023-12-12","paper":"/paper/expand-and-quantize-unsupervised-semantic","paper_url":"https://arxiv.org/abs/2312.07342v1","paper_title":"Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"DepthG (ViT-S/8)","metrics":{"Clustering [Accuracy]":"56.3","Clustering [mIoU]":"25.6","Linear Classifier [Accuracy]":"73.7","Linear Classifier [mIoU]":"38.9"},"uses_additional_data":false,"paper_date":"2023-09-21","paper":"/paper/spatially-guiding-unsupervised-semantic","paper_url":"https://arxiv.org/abs/2309.12378v2","paper_title":"Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling","code":"https://github.com/leonsick/depthg","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"PriMaPs+HP (DINO ViT-S/8)","metrics":{"Clustering [Accuracy]":"57.8","Clustering [mIoU]":"25.1"},"uses_additional_data":false,"paper_date":"2024-04-25","paper":"/paper/boosting-unsupervised-semantic-segmentation","paper_url":"https://arxiv.org/abs/2404.16818v2","paper_title":"Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals","code":"https://github.com/visinf/primaps","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"HP (ViT-S/8)","metrics":{"Clustering [Accuracy]":"57.2","Clustering [mIoU]":"24.6","Linear Classifier [Accuracy]":"75.6","Linear Classifier [mIoU]":"42.7"},"uses_additional_data":false,"paper_date":"2023-03-27","paper":"/paper/leveraging-hidden-positives-for-unsupervised","paper_url":"https://arxiv.org/abs/2303.15014v1","paper_title":"Leveraging Hidden Positives for Unsupervised Semantic Segmentation","code":"https://github.com/hynnsk/hp","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"STEGO (ViT-S/8)","metrics":{"Clustering [mIoU]":"24.5","Linear Classifier [Accuracy]":"74.4","Linear Classifier [mIoU]":"38.3"},"uses_additional_data":false,"paper_date":"2022-03-16","paper":"/paper/unsupervised-semantic-segmentation-by-2","paper_url":"https://arxiv.org/abs/2203.08414v1","paper_title":"Unsupervised Semantic Segmentation by Distilling Feature Correspondences","code":"https://github.com/mhamilton723/STEGO","n_code_links":3,"syntology":{"n_ran":8,"n_unverified":6,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"HP (ViT-S/16)","metrics":{"Clustering [Accuracy]":"54.5","Clustering [mIoU]":"24.3","Linear Classifier [Accuracy]":"74.1","Linear Classifier [mIoU]":"39.1"},"uses_additional_data":false,"paper_date":"2023-03-27","paper":"/paper/leveraging-hidden-positives-for-unsupervised","paper_url":"https://arxiv.org/abs/2303.15014v1","paper_title":"Leveraging Hidden Positives for Unsupervised Semantic Segmentation","code":"https://github.com/hynnsk/hp","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"CrOC (ViT-S/16, COCO+)","metrics":{"Clustering [mIoU]":"21.9"},"uses_additional_data":false,"paper_date":"2023-03-23","paper":"/paper/croc-cross-view-online-clustering-for-dense","paper_url":"https://arxiv.org/abs/2303.13245v1","paper_title":"CrOC: Cross-View Online Clustering for Dense Visual Representation Learning","code":"https://github.com/stegmuel/croc","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"ViCE","metrics":{"Clustering [Accuracy]":"64.8","Clustering [mIoU]":"21.77"},"uses_additional_data":false,"paper_date":"2021-11-24","paper":"/paper/vice-self-supervised-visual-concept","paper_url":"https://arxiv.org/abs/2111.12460v3","paper_title":"ViCE: Improving Dense Representation Learning by Superpixelization and Contrasting Cluster Assignment","code":"https://github.com/robin-karlsson0/vice","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"FS4","metrics":{"Clustering [Accuracy]":"40.38","Clustering [mIoU]":"15.69"},"uses_additional_data":false,"paper_date":"2022-02-24","paper":"/paper/fully-self-supervised-learning-for-semantic","paper_url":"https://arxiv.org/abs/2202.11981v1","paper_title":"Fully Self-Supervised Learning for Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"PiCIE + H","metrics":{"Clustering [Accuracy]":"49.99","Clustering [mIoU]":"14.36"},"uses_additional_data":false,"paper_date":"2021-03-30","paper":"/paper/picie-unsupervised-semantic-segmentation","paper_url":"https://arxiv.org/abs/2103.17070v1","paper_title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","code":"https://github.com/janghyuncho/PiCIE","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":23,"model":"SGSeg","metrics":{"Clustering [Accuracy]":"55.7"},"uses_additional_data":false,"paper_date":"2022-10-21","paper":"/paper/unsupervised-image-semantic-segmentation","paper_url":"https://arxiv.org/abs/2210.11810v1","paper_title":"Unsupervised Image Semantic Segmentation through Superpixels and Graph Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"SAN","metrics":{"Clustering [Accuracy]":"52.0"},"uses_additional_data":false,"paper_date":"2022-11-26","paper":"/paper/rethinking-alignment-and-uniformity-in","paper_url":"https://arxiv.org/abs/2211.14513v3","paper_title":"Rethinking Alignment and Uniformity in Unsupervised Semantic Segmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":25,"model":"PiCIE","metrics":{"Clustering [Accuracy]":"48.1"},"uses_additional_data":false,"paper_date":"2021-03-30","paper":"/paper/picie-unsupervised-semantic-segmentation","paper_url":"https://arxiv.org/abs/2103.17070v1","paper_title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","code":"https://github.com/janghyuncho/PiCIE","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":26,"model":"Ours (SlotCon)","metrics":{"Clustering [Accuracy]":"42.36"},"uses_additional_data":false,"paper_date":"2022-05-30","paper":"/paper/self-supervised-visual-representation-2","paper_url":"https://arxiv.org/abs/2205.15288v2","paper_title":"Self-Supervised Visual Representation Learning with Semantic Grouping","code":"https://github.com/CVMI-Lab/SlotCon","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"IIC","metrics":{"Clustering [Accuracy]":"21.8"},"uses_additional_data":false,"paper_date":"2018-07-17","paper":"/paper/invariant-information-distillation-for","paper_url":"https://arxiv.org/abs/1807.06653v4","paper_title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","code":"https://github.com/xu-ji/IIC","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":16,"n_samples":18,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"HCL (ViT-S/8)","metrics":{"Linear Classifier [Accuracy]":"77.3","Linear Classifier [mIoU]":"47.4"},"uses_additional_data":false,"paper_date":"2025-04-29","paper":"/paper/hierarchical-context-learning-of-object","paper_url":"https://www.sciencedirect.com/science/article/pii/S0031320325003735","paper_title":"Hierarchical Context Learning of object components for unsupervised semantic segmentation","code":"https://github.com/dbaofd/HCL","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"HCL (ViT-S/16)","metrics":{"Linear Classifier [Accuracy]":"76.7","Linear Classifier [mIoU]":"45.8"},"uses_additional_data":false,"paper_date":"2025-04-29","paper":"/paper/hierarchical-context-learning-of-object","paper_url":"https://www.sciencedirect.com/science/article/pii/S0031320325003735","paper_title":"Hierarchical Context Learning of object components for unsupervised semantic segmentation","code":"https://github.com/dbaofd/HCL","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":12,"rows_with_any_sample_ran":12,"distinct_papers_with_graph_line":9,"distinct_papers_with_any_sample_ran":9,"samples_over_distinct_papers":{"n_ran":49,"n_unverified":37,"n_samples":86,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":60,"n_unverified":47,"n_samples":107,"n_pointer_only_licence":2,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}