{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/measuring-robustness-to-natural-distribution","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","arxiv_id":"2007.00644","date":"2020-07-01","proceeding":"NeurIPS 2020 12","authors":["Rohan Taori","Achal Dave","Vaishaal Shankar","Nicholas Carlini","Benjamin Recht","Ludwig Schmidt"],"abstract":"We study how robust current ImageNet models are to distribution shifts arising from natural variations in datasets. Most research on robustness focuses on synthetic image perturbations (noise, simulated weather artifacts, adversarial examples, etc.), which leaves open how robustness on synthetic distribution shift relates to distribution shift arising in real data. Informed by an evaluation of 204 ImageNet models in 213 different test conditions, we find that there is often little to no transfer of robustness from current synthetic to natural distribution shift. Moreover, most current techniques provide no robustness to the natural distribution shifts in our testbed. The main exception is training on larger and more diverse datasets, which in multiple cases increases robustness, but is still far from closing the performance gaps. Our results indicate that distribution shifts arising in real data are currently an open research problem. We provide our testbed and data as a resource for future work at https://modestyachts.github.io/imagenet-testbed/ .","url_abs":"https://arxiv.org/abs/2007.00644v2","url_pdf":"https://arxiv.org/pdf/2007.00644v2.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":"measuring-robustness-to-natural-distribution","repo_url":"https://github.com/modestyachts/imagenet-testbed","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (IN-C)","rank_in_archive_order":41,"of":90,"metrics":{"Accuracy - All Images":"38.8","Accuracy - Clean Images":"42.9","Accuracy - Corrupted Images":"33.6"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (IN-C_brightness)","rank_in_archive_order":42,"of":90,"metrics":{"Accuracy - All Images":"38.8","Accuracy - Clean Images":"43.5","Accuracy - Corrupted Images":"32.5"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (IN-C_spatter)","rank_in_archive_order":48,"of":90,"metrics":{"Accuracy - All Images":"38.3","Accuracy - Clean Images":"42.7","Accuracy - Corrupted Images":"31.4"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (IN-C_saturate)","rank_in_archive_order":50,"of":90,"metrics":{"Accuracy - All Images":"38.2","Accuracy - Clean Images":"42.4","Accuracy - Corrupted Images":"32.4"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (IN-C_pixelate)","rank_in_archive_order":52,"of":90,"metrics":{"Accuracy - All Images":"37.4","Accuracy - Clean Images":"41.4","Accuracy - Corrupted Images":"30.9"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (IN-C_contrast)","rank_in_archive_order":59,"of":90,"metrics":{"Accuracy - All Images":"36.5","Accuracy - Clean Images":"40.9","Accuracy - Corrupted Images":"30.7"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (IN-C_jpeg_compression)","rank_in_archive_order":60,"of":90,"metrics":{"Accuracy - All Images":"36.5","Accuracy - Clean Images":"41.3","Accuracy - Corrupted Images":"30.3"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (IN-C_gaussian_noise)","rank_in_archive_order":61,"of":90,"metrics":{"Accuracy - All Images":"36.4","Accuracy - Clean Images":"40.6","Accuracy - Corrupted Images":"30.2"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (IN-C_frost)","rank_in_archive_order":63,"of":90,"metrics":{"Accuracy - All Images":"36.1","Accuracy - Clean Images":"40","Accuracy - Corrupted Images":"29.7"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (IN-C_fog_aws)","rank_in_archive_order":65,"of":90,"metrics":{"Accuracy - All Images":"35.9","Accuracy - Clean Images":"39.9","Accuracy - Corrupted Images":"30.3"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (IN-C_motion_blur)","rank_in_archive_order":67,"of":90,"metrics":{"Accuracy - All Images":"35.7","Accuracy - Clean Images":"39.6","Accuracy - Corrupted Images":"30.2"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (IN-C_zoom_blur)","rank_in_archive_order":81,"of":90,"metrics":{"Accuracy - All Images":"32.7","Accuracy - Clean Images":"36.6","Accuracy - Corrupted Images":"28.3"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (IN-C_greyscale)","rank_in_archive_order":84,"of":90,"metrics":{"Accuracy - All Images":"30.2","Accuracy - Clean Images":"34.3","Accuracy - Corrupted Images":"24.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.00644","atlas_url":"https://app.syntology.ai/?focus=2007.00644","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2007.00644"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2007.00644\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2007.00644"},"call":"get_concepts_for_paper(arxiv_id=\"2007.00644\")"}],"by_repo":[{"repo":"modestyachts/imagenet-testbed","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2107.04649"],"harvested_for_calls":[{"arxiv_id":"2107.04649","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2107.04649"},"call":"get_harvested_code_for_paper(arxiv_id=\"2107.04649\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5cfa0287efd2049197cb1f3e7534352e3a3ceec10c3ed052471c408d6915e061","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}