{"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/dynamic-metric-learning-towards-a-scalable","title":"Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales","arxiv_id":"2103.11781","date":"2021-03-22","proceeding":"CVPR 2021 1","authors":["Yifan Sun","Yuke Zhu","Yuhan Zhang","Pengkun Zheng","Xi Qiu","Chi Zhang","Yichen Wei"],"abstract":"This paper introduces a new fundamental characteristic, \\ie, the dynamic range, from real-world metric tools to deep visual recognition. In metrology, the dynamic range is a basic quality of a metric tool, indicating its flexibility to accommodate various scales. Larger dynamic range offers higher flexibility. In visual recognition, the multiple scale problem also exist. Different visual concepts may have different semantic scales. For example, ``Animal'' and ``Plants'' have a large semantic scale while ``Elk'' has a much smaller one. Under a small semantic scale, two different elks may look quite \\emph{different} to each other . However, under a large semantic scale (\\eg, animals and plants), these two elks should be measured as being \\emph{similar}. %We argue that such flexibility is also important for deep metric learning, because different visual concepts indeed correspond to different semantic scales. Introducing the dynamic range to deep metric learning, we get a novel computer vision task, \\ie, the Dynamic Metric Learning. It aims to learn a scalable metric space to accommodate visual concepts across multiple semantic scales. Based on three types of images, \\emph{i.e.}, vehicle, animal and online products, we construct three datasets for Dynamic Metric Learning. We benchmark these datasets with popular deep metric learning methods and find Dynamic Metric Learning to be very challenging. The major difficulty lies in a conflict between different scales: the discriminative ability under a small scale usually compromises the discriminative ability under a large one, and vice versa. As a minor contribution, we propose Cross-Scale Learning (CSL) to alleviate such conflict. We show that CSL consistently improves the baseline on all the three datasets. The datasets and the code will be publicly available at https://github.com/SupetZYK/DynamicMetricLearning.","url_abs":"https://arxiv.org/abs/2103.11781v1","url_pdf":"https://arxiv.org/pdf/2103.11781v1.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":"dynamic-metric-learning-towards-a-scalable","repo_url":"https://github.com/SupetZYK/DynamicMetricLearning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[{"method_slug":"csl","method_name":"CSL"}],"datasets_introduced":[{"slug":"dyml-animal","name":"DyML-Animal","full_name":"Dynamic Metric Learning Animal"},{"slug":"dyml-product","name":"DyML-Product","full_name":"Dynamic Metric Learning Product"},{"slug":"dyml-vehicle","name":"DyML-Vehicle","full_name":"Dynamic Metric Learning Vehicle"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/metric-learning-on-dyml-animal","task":"Metric Learning","dataset":"DyML-Animal","model":"CSL","rank_in_archive_order":2,"of":2,"metrics":{"Average-mAP":"31.0"},"uses_additional_data":false},{"leaderboard":"/sota/metric-learning-on-dyml-product","task":"Metric Learning","dataset":"DyML-Product","model":"CSL","rank_in_archive_order":2,"of":2,"metrics":{"Average-mAP":"28.7"},"uses_additional_data":true},{"leaderboard":"/sota/metric-learning-on-dyml-vehicle","task":"Metric Learning","dataset":"DyML-Vehicle","model":"CSL","rank_in_archive_order":2,"of":2,"metrics":{"Average-mAP":"12.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.11781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11781"}},"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":"deterministic:regex_extraction","url":"https://github.com/SupetZYK/DynamicMetricLearning","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/MalongTech/imaterialist-product-2019","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"745995005f5cdafd","entry":"Resnet","repo":"SupetZYK/DynamicMetricLearning","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/SupetZYK/DynamicMetricLearning/blob/HEAD/src/model.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":"745995005f5cdafd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}