{"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/on-the-intrinsic-dimensionality-of-face","title":"On the Intrinsic Dimensionality of Image Representations","arxiv_id":"1803.09672","date":"2018-03-26","proceeding":"CVPR 2019 6","authors":["Sixue Gong","Vishnu Naresh Boddeti","Anil K. Jain"],"abstract":"This paper addresses the following questions pertaining to the intrinsic\ndimensionality of any given image representation: (i) estimate its intrinsic\ndimensionality, (ii) develop a deep neural network based non-linear mapping,\ndubbed DeepMDS, that transforms the ambient representation to the minimal\nintrinsic space, and (iii) validate the veracity of the mapping through image\nmatching in the intrinsic space. Experiments on benchmark image datasets (LFW,\nIJB-C and ImageNet-100) reveal that the intrinsic dimensionality of deep neural\nnetwork representations is significantly lower than the dimensionality of the\nambient features. For instance, SphereFace's 512-dim face representation and\nResNet's 512-dim image representation have an intrinsic dimensionality of 16\nand 19 respectively. Further, the DeepMDS mapping is able to obtain a\nrepresentation of significantly lower dimensionality while maintaining\ndiscriminative ability to a large extent, 59.75% TAR @ 0.1% FAR in 16-dim vs\n71.26% TAR in 512-dim on IJB-C and a Top-1 accuracy of 77.0% at 19-dim vs 83.4%\nat 512-dim on ImageNet-100.","url_abs":"http://arxiv.org/abs/1803.09672v2","url_pdf":"http://arxiv.org/pdf/1803.09672v2.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":"on-the-intrinsic-dimensionality-of-face","repo_url":"https://github.com/ansuini/IntrinsicDimDeep","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"on-the-intrinsic-dimensionality-of-face","repo_url":"https://github.com/human-analysis/intrinsic-dimensionality","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"tar","task_name":"TAR"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1803.09672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.09672"}},"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/human-analysis/intrinsic-dimensionality","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ansuini/IntrinsicDimDeep","reach":null}],"summary":{"ran_fixture":1,"ran_violates":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"listed":{"samples":5,"ran":4,"repositories":2}},"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":5,"samples":[{"code_sha256_prefix":"ccc4b5af2dd293b4","entry":"estimate","repo":"ansuini/IntrinsicDimDeep","repo_kind":"listed","path":"IDNN/intrinsic_dimension.py","file_url":"https://github.com/ansuini/IntrinsicDimDeep/blob/HEAD/IDNN/intrinsic_dimension.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ccc4b5af2dd293b4"}},{"code_sha256_prefix":"073babdc8a31a49d","entry":"func","repo":"human-analysis/intrinsic-dimensionality","repo_kind":"listed","path":"ID_estimate/ID_graph_largedata.py","file_url":"https://github.com/human-analysis/intrinsic-dimensionality/blob/HEAD/ID_estimate/ID_graph_largedata.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"073babdc8a31a49d"}},{"code_sha256_prefix":"2dd9d4c0d088fd30","entry":"func2","repo":"human-analysis/intrinsic-dimensionality","repo_kind":"listed","path":"ID_estimate/ID_graph_largedata.py","file_url":"https://github.com/human-analysis/intrinsic-dimensionality/blob/HEAD/ID_estimate/ID_graph_largedata.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2dd9d4c0d088fd30"}},{"code_sha256_prefix":"212082efcdf44d4a","entry":"func3","repo":"human-analysis/intrinsic-dimensionality","repo_kind":"listed","path":"ID_estimate/ID_graph_largedata.py","file_url":"https://github.com/human-analysis/intrinsic-dimensionality/blob/HEAD/ID_estimate/ID_graph_largedata.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"212082efcdf44d4a"}},{"code_sha256_prefix":"a08dafa105c5c01e","entry":"block_analysis","repo":"ansuini/IntrinsicDimDeep","repo_kind":"listed","path":"IDNN/intrinsic_dimension.py","file_url":"https://github.com/ansuini/IntrinsicDimDeep/blob/HEAD/IDNN/intrinsic_dimension.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":"a08dafa105c5c01e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}