{"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/compress-self-supervised-learning-by","title":"CompRess: Self-Supervised Learning by Compressing Representations","arxiv_id":"2010.14713","date":"2020-10-28","proceeding":"NeurIPS 2020 12","authors":["Soroush Abbasi Koohpayegani","Ajinkya Tejankar","Hamed Pirsiavash"],"abstract":"Self-supervised learning aims to learn good representations with unlabeled data. Recent works have shown that larger models benefit more from self-supervised learning than smaller models. As a result, the gap between supervised and self-supervised learning has been greatly reduced for larger models. In this work, instead of designing a new pseudo task for self-supervised learning, we develop a model compression method to compress an already learned, deep self-supervised model (teacher) to a smaller one (student). We train the student model so that it mimics the relative similarity between the data points in the teacher's embedding space. For AlexNet, our method outperforms all previous methods including the fully supervised model on ImageNet linear evaluation (59.0% compared to 56.5%) and on nearest neighbor evaluation (50.7% compared to 41.4%). To the best of our knowledge, this is the first time a self-supervised AlexNet has outperformed supervised one on ImageNet classification. Our code is available here: https://github.com/UMBCvision/CompRess","url_abs":"https://arxiv.org/abs/2010.14713v1","url_pdf":"https://arxiv.org/pdf/2010.14713v1.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":"compress-self-supervised-learning-by","repo_url":"https://github.com/UMBCvision/CompReSS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"linear-evaluation","task_name":"Linear evaluation"},{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.14713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.14713"}},"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/UMBCvision/CompReSS","reach":null}],"summary":{"ran_honours":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":"4b168fddd9c6f72d","entry":"get_channels","repo":"UMBCvision/CompReSS","repo_kind":"official","path":"eval_linear.py","file_url":"https://github.com/UMBCvision/CompReSS/blob/HEAD/eval_linear.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b168fddd9c6f72d"}},{"code_sha256_prefix":"d4ea389f7d00f195","entry":"normalize","repo":"UMBCvision/CompReSS","repo_kind":"official","path":"eval_knn.py","file_url":"https://github.com/UMBCvision/CompReSS/blob/HEAD/eval_knn.py","link_basis":"first_harvest_node","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":"d4ea389f7d00f195"}},{"code_sha256_prefix":"5db01358b992891c","entry":"validate","repo":"UMBCvision/CompReSS","repo_kind":"official","path":"eval_linear.py","file_url":"https://github.com/UMBCvision/CompReSS/blob/HEAD/eval_linear.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":"5db01358b992891c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}