{"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/diva-diverse-visual-feature-aggregation","title":"DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning","arxiv_id":"2004.13458","date":"2020-04-28","proceeding":"ECCV 2020 8","authors":["Timo Milbich","Karsten Roth","Homanga Bharadhwaj","Samarth Sinha","Yoshua Bengio","Björn Ommer","Joseph Paul Cohen"],"abstract":"Visual Similarity plays an important role in many computer vision applications. Deep metric learning (DML) is a powerful framework for learning such similarities which not only generalize from training data to identically distributed test distributions, but in particular also translate to unknown test classes. However, its prevailing learning paradigm is class-discriminative supervised training, which typically results in representations specialized in separating training classes. For effective generalization, however, such an image representation needs to capture a diverse range of data characteristics. To this end, we propose and study multiple complementary learning tasks, targeting conceptually different data relationships by only resorting to the available training samples and labels of a standard DML setting. Through simultaneous optimization of our tasks we learn a single model to aggregate their training signals, resulting in strong generalization and state-of-the-art performance on multiple established DML benchmark datasets.","url_abs":"https://arxiv.org/abs/2004.13458v4","url_pdf":"https://arxiv.org/pdf/2004.13458v4.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":"diva-diverse-visual-feature-aggregation","repo_url":"https://github.com/Confusezius/ECCV2020_DiVA_MultiFeature_DML","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"diva-diverse-visual-feature-aggregation","repo_url":"https://github.com/wzzheng/DCML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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":"ResNet50 + DiVA","rank_in_archive_order":21,"of":36,"metrics":{"R@1":"87.6"},"uses_additional_data":true},{"leaderboard":"/sota/metric-learning-on-cub-200-2011","task":"Metric Learning","dataset":"CUB-200-2011","model":"ResNet50 + DiVA","rank_in_archive_order":14,"of":30,"metrics":{"R@1":"69.2"},"uses_additional_data":true},{"leaderboard":"/sota/metric-learning-on-stanford-online-products-1","task":"Metric Learning","dataset":"Stanford Online Products","model":"ResNet50 + DiVA","rank_in_archive_order":25,"of":33,"metrics":{"R@1":"79.6"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.13458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13458"}},"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/DCML","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Confusezius/ECCV2020_DiVA_MultiFeature_DML","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1},"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":3,"samples":[{"code_sha256_prefix":"4b9f06999c1f936d","entry":"diva_parameters","repo":"Confusezius/ECCV2020_DiVA_MultiFeature_DML","repo_kind":"official","path":"parameters.py","file_url":"https://github.com/Confusezius/ECCV2020_DiVA_MultiFeature_DML/blob/HEAD/parameters.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4b9f06999c1f936d"}},{"code_sha256_prefix":"fce7ae6b608c23d7","entry":"wandb_parameters","repo":"Confusezius/ECCV2020_DiVA_MultiFeature_DML","repo_kind":"official","path":"parameters.py","file_url":"https://github.com/Confusezius/ECCV2020_DiVA_MultiFeature_DML/blob/HEAD/parameters.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fce7ae6b608c23d7"}},{"code_sha256_prefix":"b4732fa1ac7c0462","entry":"basic_training_parameters","repo":"Confusezius/ECCV2020_DiVA_MultiFeature_DML","repo_kind":"official","path":"parameters.py","file_url":"https://github.com/Confusezius/ECCV2020_DiVA_MultiFeature_DML/blob/HEAD/parameters.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b4732fa1ac7c0462"}},{"code_sha256_prefix":"24577f28972a8fb5","entry":"basic_training_parameters","repo":"wzzheng/DCML","repo_kind":"listed","path":"parameters.py","file_url":"https://github.com/wzzheng/DCML/blob/HEAD/parameters.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":"24577f28972a8fb5"}},{"code_sha256_prefix":"c6eb06551ccfdea1","entry":"diva_parameters","repo":"wzzheng/DCML","repo_kind":"listed","path":"parameters.py","file_url":"https://github.com/wzzheng/DCML/blob/HEAD/parameters.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":"c6eb06551ccfdea1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}