{"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/deep-metric-learning-with-bier-boosting","title":"Deep Metric Learning with BIER: Boosting Independent Embeddings Robustly","arxiv_id":"1801.04815","date":"2018-01-15","proceeding":null,"authors":["Michael Opitz","Georg Waltner","Horst Possegger","Horst Bischof"],"abstract":"Learning similarity functions between image pairs with deep neural networks\nyields highly correlated activations of embeddings. In this work, we show how\nto improve the robustness of such embeddings by exploiting the independence\nwithin ensembles. To this end, we divide the last embedding layer of a deep\nnetwork into an embedding ensemble and formulate training this ensemble as an\nonline gradient boosting problem. Each learner receives a reweighted training\nsample from the previous learners. Further, we propose two loss functions which\nincrease the diversity in our ensemble. These loss functions can be applied\neither for weight initialization or during training. Together, our\ncontributions leverage large embedding sizes more effectively by significantly\nreducing correlation of the embedding and consequently increase retrieval\naccuracy of the embedding. Our method works with any differentiable loss\nfunction and does not introduce any additional parameters during test time. We\nevaluate our metric learning method on image retrieval tasks and show that it\nimproves over state-of-the-art methods on the CUB 200-2011, Cars-196, Stanford\nOnline Products, In-Shop Clothes Retrieval and VehicleID datasets.","url_abs":"http://arxiv.org/abs/1801.04815v1","url_pdf":"http://arxiv.org/pdf/1801.04815v1.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":"deep-metric-learning-with-bier-boosting","repo_url":"https://github.com/mop/bier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"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-sop","task":"Image Retrieval","dataset":"SOP","model":"A-BIER","rank_in_archive_order":13,"of":14,"metrics":{"R@1":"74.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.04815","atlas_url":"https://app.syntology.ai/?focus=1801.04815","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":"1801.04815"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1801.04815\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1801.04815"},"call":"get_concepts_for_paper(arxiv_id=\"1801.04815\")"}],"by_repo":[{"repo":"mop/bier","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"211df768143a9074a63207dc5644b3147a2cd22764e3f0a6e44a2a0d5a45e9a4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}