{"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/improved-embeddings-with-easy-positive","title":"Improved Embeddings with Easy Positive Triplet Mining","arxiv_id":"1904.04370","date":"2019-04-08","proceeding":null,"authors":["Hong Xuan","Abby Stylianou","Robert Pless"],"abstract":"Deep metric learning seeks to define an embedding where semantically similar images are embedded to nearby locations, and semantically dissimilar images are embedded to distant locations. Substantial work has focused on loss functions and strategies to learn these embeddings by pushing images from the same class as close together in the embedding space as possible. In this paper, we propose an alternative, loosened embedding strategy that requires the embedding function only map each training image to the most similar examples from the same class, an approach we call \"Easy Positive\" mining. We provide a collection of experiments and visualizations that highlight that this Easy Positive mining leads to embeddings that are more flexible and generalize better to new unseen data. This simple mining strategy yields recall performance that exceeds state of the art approaches (including those with complicated loss functions and ensemble methods) on image retrieval datasets including CUB, Stanford Online Products, In-Shop Clothes and Hotels-50K.","url_abs":"https://arxiv.org/abs/1904.04370v2","url_pdf":"https://arxiv.org/pdf/1904.04370v2.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":"improved-embeddings-with-easy-positive","repo_url":"https://github.com/littleredxh/EasyPositiveHardNegative","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"improved-embeddings-with-easy-positive","repo_url":"https://github.com/SilverIonn/EPHN-OpenSet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"improved-embeddings-with-easy-positive","repo_url":"https://github.com/littleredxh/DREML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-on-cars196","task":"Image Retrieval","dataset":"CARS196","model":"EPSHN512","rank_in_archive_order":7,"of":8,"metrics":{"R@1":"82.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-cub-200-2011","task":"Image Retrieval","dataset":"CUB-200-2011","model":"EPSHN512","rank_in_archive_order":8,"of":8,"metrics":{"R@1":"64.9"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-in-shop","task":"Image Retrieval","dataset":"In-Shop","model":"EPSHN512","rank_in_archive_order":6,"of":7,"metrics":{"R@1":"87.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-sop","task":"Image Retrieval","dataset":"SOP","model":"EPSHN512","rank_in_archive_order":10,"of":14,"metrics":{"R@1":"78.3"},"uses_additional_data":false},{"leaderboard":"/sota/metric-learning-on-cars196","task":"Metric Learning","dataset":"CARS196","model":"EPSHN(512)","rank_in_archive_order":31,"of":36,"metrics":{"R@1":"82.7"},"uses_additional_data":false},{"leaderboard":"/sota/metric-learning-on-cars196","task":"Metric Learning","dataset":"CARS196","model":"EPSHN(64)","rank_in_archive_order":35,"of":36,"metrics":{"R@1":"75.5"},"uses_additional_data":false},{"leaderboard":"/sota/metric-learning-on-cub-200-2011","task":"Metric Learning","dataset":"CUB-200-2011","model":"EPSHN(512)","rank_in_archive_order":22,"of":30,"metrics":{"R@1":"64.9"},"uses_additional_data":false},{"leaderboard":"/sota/metric-learning-on-cub-200-2011","task":"Metric Learning","dataset":"CUB-200-2011","model":"EPSHN(64)","rank_in_archive_order":29,"of":30,"metrics":{"R@1":"57.3"},"uses_additional_data":false},{"leaderboard":"/sota/metric-learning-on-in-shop-1","task":"Metric Learning","dataset":"In-Shop","model":"EPSHN(512)","rank_in_archive_order":15,"of":15,"metrics":{"R@1":"87.8"},"uses_additional_data":false},{"leaderboard":"/sota/metric-learning-on-stanford-online-products-1","task":"Metric Learning","dataset":"Stanford Online Products","model":"EPSHN(512)","rank_in_archive_order":29,"of":33,"metrics":{"R@1":"78.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.04370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.04370"}},"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/littleredxh/DREML","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SilverIonn/EPHN-OpenSet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/littleredxh/EasyPositiveHardNegative","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"2bc3d01ae11b264d","entry":"RP","repo":"littleredxh/EasyPositiveHardNegative","repo_kind":"official","path":"_code/Utils.py","file_url":"https://github.com/littleredxh/EasyPositiveHardNegative/blob/HEAD/_code/Utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2bc3d01ae11b264d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}