{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/cross-batch-memory-for-embedding-learning","title":"Cross-Batch Memory for Embedding Learning","arxiv_id":"1912.06798","date":"2019-12-14","proceeding":"CVPR 2020 6","authors":["Xun Wang","Haozhi Zhang","Weilin Huang","Matthew R. Scott"],"abstract":"Mining informative negative instances are of central importance to deep metric learning (DML), however this task is intrinsically limited by mini-batch training, where only a mini-batch of instances is accessible at each iteration. In this paper, we identify a \"slow drift\" phenomena by observing that the embedding features drift exceptionally slow even as the model parameters are updating throughout the training process. This suggests that the features of instances computed at preceding iterations can be used to considerably approximate their features extracted by the current model. We propose a cross-batch memory (XBM) mechanism that memorizes the embeddings of past iterations, allowing the model to collect sufficient hard negative pairs across multiple mini-batches - even over the whole dataset. Our XBM can be directly integrated into a general pair-based DML framework, where the XBM augmented DML can boost performance considerably. In particular, without bells and whistles, a simple contrastive loss with our XBM can have large R@1 improvements of 12%-22.5% on three large-scale image retrieval datasets, surpassing the most sophisticated state-of-the-art methods, by a large margin. Our XBM is conceptually simple, easy to implement - using several lines of codes, and is memory efficient - with a negligible 0.2 GB extra GPU memory. Code is available at: https://github.com/MalongTech/research-xbm.","url_abs":"https://arxiv.org/abs/1912.06798v3","url_pdf":"https://arxiv.org/pdf/1912.06798v3.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":"cross-batch-memory-for-embedding-learning","repo_url":"https://github.com/MalongTech/research-xbm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"cross-batch-memory-for-embedding-learning","repo_url":"https://github.com/bnu-wangxun/Deep_Metric","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cross-batch-memory-for-embedding-learning","repo_url":"https://github.com/msight-tech/research-xbm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"cross-batch-memory-for-embedding-learning","repo_url":"https://github.com/OML-Team/open-metric-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"cross-batch-memory-for-embedding-learning","repo_url":"https://github.com/PaddlePaddle/PaddleClas/blob/develop/docs/zh_CN/training/metric_learning/xbm.md","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-in-shop","task":"Image Retrieval","dataset":"In-Shop","model":"Cross-Batch Memory","rank_in_archive_order":2,"of":7,"metrics":{"R@1":"91.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-sop","task":"Image Retrieval","dataset":"SOP","model":"Cross-Batch Memory","rank_in_archive_order":7,"of":14,"metrics":{"R@1":"80.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1912.06798","atlas_url":"https://app.syntology.ai/?focus=1912.06798","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1912.06798"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1912.06798\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1912.06798"},"call":"get_concepts_for_paper(arxiv_id=\"1912.06798\")"}],"by_repo":[{"repo":"MalongTech/research-xbm","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"bnu-wangxun/Deep_Metric","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1904.06627"],"harvested_for_calls":[{"arxiv_id":"1904.06627","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1904.06627"},"call":"get_harvested_code_for_paper(arxiv_id=\"1904.06627\")"}]},{"repo":"msight-tech/research-xbm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"OML-Team/open-metric-learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2010.11929"],"harvested_for_calls":[{"arxiv_id":"2010.11929","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.11929"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.11929\")"}]},{"repo":"PaddlePaddle/PaddleClas","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1a69af9db4f7e4ac7163a5e21ae6b14ad0cebd38eb8b79462b43cefe9fb9642e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}