{"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/on-feature-decorrelation-in-self-supervised","title":"On Feature Decorrelation in Self-Supervised Learning","arxiv_id":"2105.00470","date":"2021-05-02","proceeding":"ICCV 2021 10","authors":["Tianyu Hua","Wenxiao Wang","Zihui Xue","Sucheng Ren","Yue Wang","Hang Zhao"],"abstract":"In self-supervised representation learning, a common idea behind most of the state-of-the-art approaches is to enforce the robustness of the representations to predefined augmentations. A potential issue of this idea is the existence of completely collapsed solutions (i.e., constant features), which are typically avoided implicitly by carefully chosen implementation details. In this work, we study a relatively concise framework containing the most common components from recent approaches. We verify the existence of complete collapse and discover another reachable collapse pattern that is usually overlooked, namely dimensional collapse. We connect dimensional collapse with strong correlations between axes and consider such connection as a strong motivation for feature decorrelation (i.e., standardizing the covariance matrix). The gains from feature decorrelation are verified empirically to highlight the importance and the potential of this insight.","url_abs":"https://arxiv.org/abs/2105.00470v2","url_pdf":"https://arxiv.org/pdf/2105.00470v2.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":"on-feature-decorrelation-in-self-supervised","repo_url":"https://github.com/PatrickHua/FeatureDecorrelationSSL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.00470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.00470"}},"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/PatrickHua/FeatureDecorrelationSSL","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":"b2429807c9efa3f7","entry":"D","repo":"PatrickHua/FeatureDecorrelationSSL","repo_kind":"official","path":"models/simsiam.py","file_url":"https://github.com/PatrickHua/FeatureDecorrelationSSL/blob/HEAD/models/simsiam.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b2429807c9efa3f7"}},{"code_sha256_prefix":"a2d406a0a54489bf","entry":"norm_mse_loss","repo":"PatrickHua/FeatureDecorrelationSSL","repo_kind":"official","path":"models/wmse.py","file_url":"https://github.com/PatrickHua/FeatureDecorrelationSSL/blob/HEAD/models/wmse.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2d406a0a54489bf"}},{"code_sha256_prefix":"93c917f76761535c","entry":"get_norm","repo":"PatrickHua/FeatureDecorrelationSSL","repo_kind":"official","path":"models/covnorm.py","file_url":"https://github.com/PatrickHua/FeatureDecorrelationSSL/blob/HEAD/models/covnorm.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":"93c917f76761535c"}},{"code_sha256_prefix":"fcaf2040c9a25a15","entry":"off_diagonal","repo":"PatrickHua/FeatureDecorrelationSSL","repo_kind":"official","path":"models/barlowtwins.py","file_url":"https://github.com/PatrickHua/FeatureDecorrelationSSL/blob/HEAD/models/barlowtwins.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":"fcaf2040c9a25a15"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}