{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/picie-unsupervised-semantic-segmentation","title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","arxiv_id":"2103.17070","date":"2021-03-30","proceeding":"CVPR 2021 1","authors":["Jang Hyun Cho","Utkarsh Mall","Kavita Bala","Bharath Hariharan"],"abstract":"We present a new framework for semantic segmentation without annotations via clustering. Off-the-shelf clustering methods are limited to curated, single-label, and object-centric images yet real-world data are dominantly uncurated, multi-label, and scene-centric. We extend clustering from images to pixels and assign separate cluster membership to different instances within each image. However, solely relying on pixel-wise feature similarity fails to learn high-level semantic concepts and overfits to low-level visual cues. We propose a method to incorporate geometric consistency as an inductive bias to learn invariance and equivariance for photometric and geometric variations. With our novel learning objective, our framework can learn high-level semantic concepts. Our method, PiCIE (Pixel-level feature Clustering using Invariance and Equivariance), is the first method capable of segmenting both things and stuff categories without any hyperparameter tuning or task-specific pre-processing. Our method largely outperforms existing baselines on COCO and Cityscapes with +17.5 Acc. and +4.5 mIoU. We show that PiCIE gives a better initialization for standard supervised training. The code is available at https://github.com/janghyuncho/PiCIE.","url_abs":"https://arxiv.org/abs/2103.17070v1","url_pdf":"https://arxiv.org/pdf/2103.17070v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"picie-unsupervised-semantic-segmentation","repo_url":"https://github.com/janghyuncho/PiCIE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"picie-unsupervised-semantic-segmentation","repo_url":"https://github.com/xmed-lab/mssg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-semantic-segmentation","task_name":"Unsupervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-6","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-171","model":"PiCIE (ResNet-50)","rank_in_archive_order":3,"of":4,"metrics":{"Pixel Accuracy":"29.8","mIoU":"5.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-7","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-27","model":"PiCIE + H","rank_in_archive_order":22,"of":29,"metrics":{"Clustering [Accuracy]":"49.99","Clustering [mIoU]":"14.36"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-7","task":"Unsupervised Semantic Segmentation","dataset":"COCO-Stuff-27","model":"PiCIE","rank_in_archive_order":25,"of":29,"metrics":{"Clustering [Accuracy]":"48.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on","task":"Unsupervised Semantic Segmentation","dataset":"Cityscapes test","model":"PiCIE","rank_in_archive_order":12,"of":14,"metrics":{"Accuracy":"65.5","mIoU":"12.3"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-6","task":"Unsupervised Semantic Segmentation","dataset":"ImageNet-S-50","model":"PiCIE (Supervised pretrain)","rank_in_archive_order":4,"of":5,"metrics":{"mIoU (test)":"17.6","mIoU (val)":"17.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.17070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.17070"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/janghyuncho/PiCIE","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xmed-lab/mssg","reach":null}],"summary":{"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"3c32fb74b4ef0f37","entry":"CSNet","repo":"xmed-lab/mssg","repo_kind":"listed","path":"SPM/model.py","file_url":"https://github.com/xmed-lab/mssg/blob/HEAD/SPM/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3c32fb74b4ef0f37"}},{"code_sha256_prefix":"fe65b7eec08e4420","entry":"FPNDecoder","repo":"janghyuncho/PiCIE","repo_kind":"official","path":"commons.py","file_url":"https://github.com/janghyuncho/PiCIE/blob/HEAD/commons.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fe65b7eec08e4420"}},{"code_sha256_prefix":"a5f6d89ab4ee2f2e","entry":"PanopticFPN","repo":"janghyuncho/PiCIE","repo_kind":"official","path":"commons.py","file_url":"https://github.com/janghyuncho/PiCIE/blob/HEAD/commons.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a5f6d89ab4ee2f2e"}},{"code_sha256_prefix":"244fef8da8d0aacf","entry":"get_model_and_optimizer","repo":"janghyuncho/PiCIE","repo_kind":"official","path":"commons.py","file_url":"https://github.com/janghyuncho/PiCIE/blob/HEAD/commons.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"244fef8da8d0aacf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}