{"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/dense-siamese-network","title":"Dense Siamese Network for Dense Unsupervised Learning","arxiv_id":"2203.11075","date":"2022-03-21","proceeding":null,"authors":["Wenwei Zhang","Jiangmiao Pang","Kai Chen","Chen Change Loy"],"abstract":"This paper presents Dense Siamese Network (DenseSiam), a simple unsupervised learning framework for dense prediction tasks. It learns visual representations by maximizing the similarity between two views of one image with two types of consistency, i.e., pixel consistency and region consistency. Concretely, DenseSiam first maximizes the pixel level spatial consistency according to the exact location correspondence in the overlapped area. It also extracts a batch of region embeddings that correspond to some sub-regions in the overlapped area to be contrasted for region consistency. In contrast to previous methods that require negative pixel pairs, momentum encoders or heuristic masks, DenseSiam benefits from the simple Siamese network and optimizes the consistency of different granularities. It also proves that the simple location correspondence and interacted region embeddings are effective enough to learn the similarity. We apply DenseSiam on ImageNet and obtain competitive improvements on various downstream tasks. We also show that only with some extra task-specific losses, the simple framework can directly conduct dense prediction tasks. On an existing unsupervised semantic segmentation benchmark, it surpasses state-of-the-art segmentation methods by 2.1 mIoU with 28% training costs. Code and models are released at https://github.com/ZwwWayne/DenseSiam.","url_abs":"https://arxiv.org/abs/2203.11075v2","url_pdf":"https://arxiv.org/pdf/2203.11075v2.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":"dense-siamese-network","repo_url":"https://github.com/zwwwayne/densesiam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-semantic-segmentation","task_name":"Unsupervised Semantic Segmentation"}],"methods":[{"method_slug":"siamese-network","method_name":"Siamese Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-semantic-segmentation-on-coco-5","task":"Unsupervised Semantic Segmentation","dataset":"COCO-All","model":"DenseSiam","rank_in_archive_order":1,"of":1,"metrics":{"mIoU":"16.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.11075","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11075"}},"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/zwwwayne/densesiam","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ZwwWayne/DenseSiam","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"f8449384e8465ac7","entry":"get_result_metrics","repo":"ZwwWayne/DenseSiam","repo_kind":"official","path":"densesiam/core/evaluators/cluster_mIoU_evaluator.py","file_url":"https://github.com/ZwwWayne/DenseSiam/blob/HEAD/densesiam/core/evaluators/cluster_mIoU_evaluator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f8449384e8465ac7"}},{"code_sha256_prefix":"0d954698d8107a2e","entry":"scores","repo":"ZwwWayne/DenseSiam","repo_kind":"official","path":"densesiam/core/evaluators/cluster_mIoU_evaluator.py","file_url":"https://github.com/ZwwWayne/DenseSiam/blob/HEAD/densesiam/core/evaluators/cluster_mIoU_evaluator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0d954698d8107a2e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}