{"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-hierarchical","title":"Deep Metric Learning with Hierarchical Triplet Loss","arxiv_id":"1810.06951","date":"2018-10-16","proceeding":"ECCV 2018 9","authors":["Weifeng Ge","Weilin Huang","Dengke Dong","Matthew R. Scott"],"abstract":"We present a novel hierarchical triplet loss (HTL) capable of automatically\ncollecting informative training samples (triplets) via a defined hierarchical\ntree that encodes global context information. This allows us to cope with the\nmain limitation of random sampling in training a conventional triplet loss,\nwhich is a central issue for deep metric learning. Our main contributions are\ntwo-fold. (i) we construct a hierarchical class-level tree where neighboring\nclasses are merged recursively. The hierarchical structure naturally captures\nthe intrinsic data distribution over the whole database. (ii) we formulate the\nproblem of triplet collection by introducing a new violate margin, which is\ncomputed dynamically based on the designed hierarchical tree. This allows it to\nautomatically select meaningful hard samples with the guide of global context.\nIt encourages the model to learn more discriminative features from visual\nsimilar classes, leading to faster convergence and better performance. Our\nmethod is evaluated on the tasks of image retrieval and face recognition, where\nit outperforms the standard triplet loss substantially by 1%-18%. It achieves\nnew state-of-the-art performance on a number of benchmarks, with much fewer\nlearning iterations.","url_abs":"http://arxiv.org/abs/1810.06951v1","url_pdf":"http://arxiv.org/pdf/1810.06951v1.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":[],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":null,"task_name":"Triplet"}],"methods":[{"method_slug":"triplet-loss","method_name":"Triplet Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-cars196","task":"Image Retrieval","dataset":"CARS196","model":"HTL","rank_in_archive_order":8,"of":8,"metrics":{"R@1":"81.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.06951","atlas_url":"https://app.syntology.ai/?focus=1810.06951","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":"1810.06951"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1810.06951\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1810.06951"},"call":"get_concepts_for_paper(arxiv_id=\"1810.06951\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"92d2f48e39ccda009d2e32ef6a479773718ae60517af85c79274e47a965a237f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}