{"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/s2sd-simultaneous-similarity-based-self","title":"S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning","arxiv_id":"2009.08348","date":"2020-09-17","proceeding":null,"authors":["Karsten Roth","Timo Milbich","Björn Ommer","Joseph Paul Cohen","Marzyeh Ghassemi"],"abstract":"Deep Metric Learning (DML) provides a crucial tool for visual similarity and zero-shot applications by learning generalizing embedding spaces, although recent work in DML has shown strong performance saturation across training objectives. However, generalization capacity is known to scale with the embedding space dimensionality. Unfortunately, high dimensional embeddings also create higher retrieval cost for downstream applications. To remedy this, we propose \\emph{Simultaneous Similarity-based Self-distillation (S2SD). S2SD extends DML with knowledge distillation from auxiliary, high-dimensional embedding and feature spaces to leverage complementary context during training while retaining test-time cost and with negligible changes to the training time. Experiments and ablations across different objectives and standard benchmarks show S2SD offers notable improvements of up to 7% in Recall@1, while also setting a new state-of-the-art. Code available at https://github.com/MLforHealth/S2SD.","url_abs":"https://arxiv.org/abs/2009.08348v3","url_pdf":"https://arxiv.org/pdf/2009.08348v3.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":"s2sd-simultaneous-similarity-based-self","repo_url":"https://github.com/MLforHealth/S2SD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/metric-learning-on-cars196","task":"Metric Learning","dataset":"CARS196","model":"ResNet50 + S2SD","rank_in_archive_order":10,"of":36,"metrics":{"R@1":"89.5"},"uses_additional_data":true},{"leaderboard":"/sota/metric-learning-on-cub-200-2011","task":"Metric Learning","dataset":"CUB-200-2011","model":"ResNet50 + S2SD","rank_in_archive_order":12,"of":30,"metrics":{"R@1":"70.1"},"uses_additional_data":true},{"leaderboard":"/sota/metric-learning-on-stanford-online-products-1","task":"Metric Learning","dataset":"Stanford Online Products","model":"ResNet50 + S2SD","rank_in_archive_order":19,"of":33,"metrics":{"R@1":"81.0"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.08348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.08348"}},"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/MLforHealth/S2SD","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":"1edf35955d77e643","entry":"basic_training_parameters","repo":"MLforHealth/S2SD","repo_kind":"official","path":"parameters.py","file_url":"https://github.com/MLforHealth/S2SD/blob/HEAD/parameters.py","link_basis":"plan_row","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":"1edf35955d77e643"}},{"code_sha256_prefix":"16a51e8478d5ab48","entry":"s2sd_parameters","repo":"MLforHealth/S2SD","repo_kind":"official","path":"parameters.py","file_url":"https://github.com/MLforHealth/S2SD/blob/HEAD/parameters.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":"16a51e8478d5ab48"}},{"code_sha256_prefix":"cf110ed7999166a5","entry":"wandb_parameters","repo":"MLforHealth/S2SD","repo_kind":"official","path":"parameters.py","file_url":"https://github.com/MLforHealth/S2SD/blob/HEAD/parameters.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":"cf110ed7999166a5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}