{"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/the-intrinsic-dimension-of-images-and-its-1","title":"The Intrinsic Dimension of Images and Its Impact on Learning","arxiv_id":"2104.08894","date":"2021-04-18","proceeding":"ICLR 2021 1","authors":["Phillip Pope","Chen Zhu","Ahmed Abdelkader","Micah Goldblum","Tom Goldstein"],"abstract":"It is widely believed that natural image data exhibits low-dimensional structure despite the high dimensionality of conventional pixel representations. This idea underlies a common intuition for the remarkable success of deep learning in computer vision. In this work, we apply dimension estimation tools to popular datasets and investigate the role of low-dimensional structure in deep learning. We find that common natural image datasets indeed have very low intrinsic dimension relative to the high number of pixels in the images. Additionally, we find that low dimensional datasets are easier for neural networks to learn, and models solving these tasks generalize better from training to test data. Along the way, we develop a technique for validating our dimension estimation tools on synthetic data generated by GANs allowing us to actively manipulate the intrinsic dimension by controlling the image generation process. Code for our experiments may be found here https://github.com/ppope/dimensions.","url_abs":"https://arxiv.org/abs/2104.08894v1","url_pdf":"https://arxiv.org/pdf/2104.08894v1.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":"the-intrinsic-dimension-of-images-and-its-1","repo_url":"https://github.com/ppope/dimensions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.08894","atlas_url":"https://app.syntology.ai/?focus=2104.08894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08894"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ppope/dimensions","reach":null}],"summary":{"ran":1,"ran_fixture":2,"ran_draft_wrong":3,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":"5a9384c8c8db2afa","entry":"KNNComputerNoCheck","repo":"ppope/dimensions","repo_kind":"official","path":"estimators/geomle.py","file_url":"https://github.com/ppope/dimensions/blob/HEAD/estimators/geomle.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a9384c8c8db2afa"}},{"code_sha256_prefix":"c3e52574ec7f8090","entry":"drop_zero_values","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"c3e52574ec7f8090"}},{"code_sha256_prefix":"df7da5b2892df07a","entry":"fit_poly_reg","repo":"ppope/dimensions","repo_kind":"official","path":"estimators/geomle.py","file_url":"https://github.com/ppope/dimensions/blob/HEAD/estimators/geomle.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df7da5b2892df07a"}},{"code_sha256_prefix":"df91d00c39eb470a","entry":"intrinsic_dim_sample_wise","repo":"ppope/dimensions","repo_kind":"official","path":"estimators/mle.py","file_url":"https://github.com/ppope/dimensions/blob/HEAD/estimators/mle.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df91d00c39eb470a"}},{"code_sha256_prefix":"71f28a5a636fea5e","entry":"intrinsic_dim_scale_interval","repo":"ppope/dimensions","repo_kind":"official","path":"estimators/mle.py","file_url":"https://github.com/ppope/dimensions/blob/HEAD/estimators/mle.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"71f28a5a636fea5e"}},{"code_sha256_prefix":"aee171526745aa8a","entry":"mle_center","repo":"ppope/dimensions","repo_kind":"official","path":"estimators/geomle.py","file_url":"https://github.com/ppope/dimensions/blob/HEAD/estimators/geomle.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aee171526745aa8a"}},{"code_sha256_prefix":"a67a7b23ea7331c5","entry":"tolist","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a67a7b23ea7331c5"}},{"code_sha256_prefix":"8f89b37d9005aa30","entry":"_func","repo":"ppope/dimensions","repo_kind":"official","path":"estimators/geomle.py","file_url":"https://github.com/ppope/dimensions/blob/HEAD/estimators/geomle.py","link_basis":"first_harvest_node","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":"8f89b37d9005aa30"}},{"code_sha256_prefix":"d52066bee0e04253","entry":"geomle","repo":"ppope/dimensions","repo_kind":"official","path":"estimators/geomle.py","file_url":"https://github.com/ppope/dimensions/blob/HEAD/estimators/geomle.py","link_basis":"first_harvest_node","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":"d52066bee0e04253"}},{"code_sha256_prefix":"7b18db6c52e2a536","entry":"update_nn","repo":"ppope/dimensions","repo_kind":"official","path":"estimators/geomle.py","file_url":"https://github.com/ppope/dimensions/blob/HEAD/estimators/geomle.py","link_basis":"first_harvest_node","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":"7b18db6c52e2a536"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}