{"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/a-non-isotropic-probabilistic-take-on-proxy","title":"A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning","arxiv_id":"2207.03784","date":"2022-07-08","proceeding":null,"authors":["Michael Kirchhof","Karsten Roth","Zeynep Akata","Enkelejda Kasneci"],"abstract":"Proxy-based Deep Metric Learning (DML) learns deep representations by embedding images close to their class representatives (proxies), commonly with respect to the angle between them. However, this disregards the embedding norm, which can carry additional beneficial context such as class- or image-intrinsic uncertainty. In addition, proxy-based DML struggles to learn class-internal structures. To address both issues at once, we introduce non-isotropic probabilistic proxy-based DML. We model images as directional von Mises-Fisher (vMF) distributions on the hypersphere that can reflect image-intrinsic uncertainties. Further, we derive non-isotropic von Mises-Fisher (nivMF) distributions for class proxies to better represent complex class-specific variances. To measure the proxy-to-image distance between these models, we develop and investigate multiple distribution-to-point and distribution-to-distribution metrics. Each framework choice is motivated by a set of ablational studies, which showcase beneficial properties of our probabilistic approach to proxy-based DML, such as uncertainty-awareness, better-behaved gradients during training, and overall improved generalization performance. The latter is especially reflected in the competitive performance on the standard DML benchmarks, where our approach compares favorably, suggesting that existing proxy-based DML can significantly benefit from a more probabilistic treatment. Code is available at github.com/ExplainableML/Probabilistic_Deep_Metric_Learning.","url_abs":"https://arxiv.org/abs/2207.03784v1","url_pdf":"https://arxiv.org/pdf/2207.03784v1.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":"a-non-isotropic-probabilistic-take-on-proxy","repo_url":"https://github.com/explainableml/probabilistic_deep_metric_learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.03784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.03784"}},"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/explainableml/probabilistic_deep_metric_learning","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ExplainableML/Probabilistic_Deep_Metric_Learning","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"331aa6e031ef162b","entry":"Criterion","repo":"ExplainableML/Probabilistic_Deep_Metric_Learning","repo_kind":"official","path":"criteria/proxynca_nivmf.py","file_url":"https://github.com/ExplainableML/Probabilistic_Deep_Metric_Learning/blob/HEAD/criteria/proxynca_nivmf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"331aa6e031ef162b"}},{"code_sha256_prefix":"9fb9e00e24461488","entry":"approx_log_cp","repo":"ExplainableML/Probabilistic_Deep_Metric_Learning","repo_kind":"official","path":"criteria/proxynca_nivmf.py","file_url":"https://github.com/ExplainableML/Probabilistic_Deep_Metric_Learning/blob/HEAD/criteria/proxynca_nivmf.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fb9e00e24461488"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}