{"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/hardness-aware-deep-metric-learning","title":"Hardness-Aware Deep Metric Learning","arxiv_id":"1903.05503","date":"2019-03-13","proceeding":"CVPR 2019 6","authors":["Wenzhao Zheng","Zhaodong Chen","Jiwen Lu","Jie zhou"],"abstract":"This paper presents a hardness-aware deep metric learning (HDML) framework. Most previous deep metric learning methods employ the hard negative mining strategy to alleviate the lack of informative samples for training. However, this mining strategy only utilizes a subset of training data, which may not be enough to characterize the global geometry of the embedding space comprehensively. To address this problem, we perform linear interpolation on embeddings to adaptively manipulate their hard levels and generate corresponding label-preserving synthetics for recycled training, so that information buried in all samples can be fully exploited and the metric is always challenged with proper difficulty. Our method achieves very competitive performance on the widely used CUB-200-2011, Cars196, and Stanford Online Products datasets.","url_abs":"https://arxiv.org/abs/1903.05503v2","url_pdf":"https://arxiv.org/pdf/1903.05503v2.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":"hardness-aware-deep-metric-learning","repo_url":"https://github.com/wzzheng/HDML","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"hardness-aware-deep-metric-learning","repo_url":"https://github.com/neka-nat/pytorch-hdml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/metric-learning-on-cars196","task":"Metric Learning","dataset":"CARS196","model":"GoogLeNet + HDML","rank_in_archive_order":34,"of":36,"metrics":{"R@1":"79.1"},"uses_additional_data":true},{"leaderboard":"/sota/metric-learning-on-cub-200-2011","task":"Metric Learning","dataset":"CUB-200-2011","model":"GoogLeNet + HDML","rank_in_archive_order":30,"of":30,"metrics":{"R@1":"53.7"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.05503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.05503"}},"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/wzzheng/HDML","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/neka-nat/pytorch-hdml","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":"3f36467f220e7ed7","entry":"cross_entropy","repo":"neka-nat/pytorch-hdml","repo_kind":"listed","path":"hdml/loss.py","file_url":"https://github.com/neka-nat/pytorch-hdml/blob/HEAD/hdml/loss.py","link_basis":"harvester_set","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":"3f36467f220e7ed7"}},{"code_sha256_prefix":"aa84ed1ace8fba4a","entry":"googlenet","repo":"neka-nat/pytorch-hdml","repo_kind":"listed","path":"hdml/googlenet.py","file_url":"https://github.com/neka-nat/pytorch-hdml/blob/HEAD/hdml/googlenet.py","link_basis":"harvester_set","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":"aa84ed1ace8fba4a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}