{"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/vision-models-are-more-robust-and-fair-when","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","arxiv_id":"2202.08360","date":"2022-02-16","proceeding":null,"authors":["Priya Goyal","Quentin Duval","Isaac Seessel","Mathilde Caron","Ishan Misra","Levent Sagun","Armand Joulin","Piotr Bojanowski"],"abstract":"Discriminative self-supervised learning allows training models on any random group of internet images, and possibly recover salient information that helps differentiate between the images. Applied to ImageNet, this leads to object centric features that perform on par with supervised features on most object-centric downstream tasks. In this work, we question if using this ability, we can learn any salient and more representative information present in diverse unbounded set of images from across the globe. To do so, we train models on billions of random images without any data pre-processing or prior assumptions about what we want the model to learn. We scale our model size to dense 10 billion parameters to avoid underfitting on a large data size. We extensively study and validate our model performance on over 50 benchmarks including fairness, robustness to distribution shift, geographical diversity, fine grained recognition, image copy detection and many image classification datasets. The resulting model, not only captures well semantic information, it also captures information about artistic style and learns salient information such as geolocations and multilingual word embeddings based on visual content only. More importantly, we discover that such model is more robust, more fair, less harmful and less biased than supervised models or models trained on object centric datasets such as ImageNet.","url_abs":"https://arxiv.org/abs/2202.08360v2","url_pdf":"https://arxiv.org/pdf/2202.08360v2.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":"vision-models-are-more-robust-and-fair-when","repo_url":"https://github.com/facebookresearch/vissl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"copy-detection","task_name":"Copy Detection"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"fairness","task_name":"Fairness"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"meme-classification","task_name":"Meme Classification"},{"task_slug":"multilingual-word-embeddings","task_name":"Multilingual Word Embeddings"},{"task_slug":"object","task_name":"Object"},{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"},{"task_slug":"traffic-sign-recognition","task_name":"Traffic Sign Recognition"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-700","task":"Action Classification","dataset":"Kinetics-700","model":"SEER (RegNet10B)","rank_in_archive_order":34,"of":36,"metrics":{"Top-1 Accuracy":"51.9"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-a","task":"Domain Generalization","dataset":"ImageNet-A","model":"SEER (RegNet10B)","rank_in_archive_order":18,"of":39,"metrics":{"Top-1 accuracy %":"52.7"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-r","task":"Domain Generalization","dataset":"ImageNet-R","model":"SEER (RegNet10B)","rank_in_archive_order":19,"of":39,"metrics":{"Top-1 Error Rate":"43.9"},"uses_additional_data":true},{"leaderboard":"/sota/domain-generalization-on-imagenet-sketch","task":"Domain Generalization","dataset":"ImageNet-Sketch","model":"SEER (RegNet10B)","rank_in_archive_order":15,"of":20,"metrics":{"Top-1 accuracy":"45.6"},"uses_additional_data":true},{"leaderboard":"/sota/fine-grained-image-classification-on-caltech","task":"Fine-Grained Image Classification","dataset":"Caltech-101","model":"SEER (RegNet10B - linear eval)","rank_in_archive_order":10,"of":18,"metrics":{"Accuracy":"91.0","Top-1 Error Rate":"9.0%"},"uses_additional_data":true},{"leaderboard":"/sota/fine-grained-image-classification-on-fgvc","task":"Fine-Grained Image Classification","dataset":"FGVC Aircraft","model":"SEER (RegNet10B)","rank_in_archive_order":54,"of":57,"metrics":{"Accuracy":"54.82%"},"uses_additional_data":true},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford-1","task":"Fine-Grained Image Classification","dataset":"Oxford-IIIT Pet Dataset","model":"SEER (RegNet10B)","rank_in_archive_order":14,"of":15,"metrics":{"Accuracy":"85.3%"},"uses_additional_data":true},{"leaderboard":"/sota/fine-grained-image-classification-on-sun397","task":"Fine-Grained Image Classification","dataset":"SUN397","model":"SEER (RegNet10B - linear eval)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"80.0"},"uses_additional_data":true},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford","task":"Fine-Grained Image Classification","dataset":"Stanford Cars","model":"SEER (RegNet10B)","rank_in_archive_order":82,"of":83,"metrics":{"Accuracy":"68.03%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"SEER (RegNet10B)","rank_in_archive_order":206,"of":265,"metrics":{"Percentage correct":"90"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"SEER (RegNet10B)","rank_in_archive_order":118,"of":211,"metrics":{"Percentage correct":"81.53"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-clevr-count","task":"Image Classification","dataset":"CLEVR/Count","model":"SEER (RegNet10B)","rank_in_archive_order":1,"of":2,"metrics":{"Top 1 Accuracy":"89.28"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-clevr-count","task":"Image Classification","dataset":"CLEVR/Count","model":"SEER (RegNetY-128GF)","rank_in_archive_order":2,"of":2,"metrics":{"Top 1 Accuracy":"87.98"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-clevr-dist","task":"Image Classification","dataset":"CLEVR/Dist","model":"SEER (RegNet10B)","rank_in_archive_order":1,"of":2,"metrics":{"Top 1 Accuracy":"74.98"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-clevr-dist","task":"Image Classification","dataset":"CLEVR/Dist","model":"SEER (RegNetY-128GF)","rank_in_archive_order":2,"of":2,"metrics":{"Top 1 Accuracy":"72.67"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-dtd","task":"Image Classification","dataset":"DTD","model":"SEER (RegNet10B - linear eval)","rank_in_archive_order":6,"of":11,"metrics":{"Accuracy":"80.5"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-eurosat","task":"Image Classification","dataset":"EuroSAT","model":"SEER (RegNet10B - linear eval)","rank_in_archive_order":13,"of":15,"metrics":{"Accuracy (%)":"97.5"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-flowers-102","task":"Image Classification","dataset":"Flowers-102","model":"SEER (RegNet10B)","rank_in_archive_order":42,"of":52,"metrics":{"Accuracy":"96.3"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-food-101-1","task":"Image Classification","dataset":"Food-101","model":"SEER (RegNet10B - linear eval)","rank_in_archive_order":4,"of":11,"metrics":{"Accuracy (%)":"90.3"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SEER (RG-10B)","rank_in_archive_order":200,"of":1060,"metrics":{"Number of params":"10000M","Top 1 Accuracy":"85.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet-real","task":"Image Classification","dataset":"ImageNet ReaL","model":"SEER (RegNet10B)","rank_in_archive_order":22,"of":57,"metrics":{"Accuracy":"89.8%","Params":"10000M"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet-v2","task":"Image Classification","dataset":"ImageNet V2","model":"SEER (RegNet10B)","rank_in_archive_order":17,"of":33,"metrics":{"Top 1 Accuracy":"76.2"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-kitti-dist","task":"Image Classification","dataset":"KITTI-Dist","model":"SEER (RegNet10B)","rank_in_archive_order":1,"of":1,"metrics":{"Top 1 Accuracy":"78.34"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"SEER (RegNet10B)","rank_in_archive_order":40,"of":81,"metrics":{"Accuracy":"99.42","Percentage error":"0.58"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"SEER (RegNet10B)","rank_in_archive_order":19,"of":106,"metrics":{"Top-1 Accuracy":"60.2"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-places205","task":"Image Classification","dataset":"Places205","model":"SEER (RegNet10B - finetuned - 384px)","rank_in_archive_order":3,"of":15,"metrics":{"Top 1 Accuracy":"69.0"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-resisc45","task":"Image Classification","dataset":"RESISC45","model":"SEER (RegNet10B)","rank_in_archive_order":5,"of":20,"metrics":{"Top 1 Accuracy":"95.61"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-resisc45","task":"Image Classification","dataset":"RESISC45","model":"SwAV (ResNet50-w5)","rank_in_archive_order":8,"of":20,"metrics":{"Top 1 Accuracy":"94.73"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-resisc45","task":"Image Classification","dataset":"RESISC45","model":"DINO (DeiT-B/16)","rank_in_archive_order":9,"of":20,"metrics":{"Top 1 Accuracy":"93.97"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-resisc45","task":"Image Classification","dataset":"RESISC45","model":"MoCo-v3 (ViT-B/16)","rank_in_archive_order":11,"of":20,"metrics":{"Top 1 Accuracy":"93.35"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-resisc45","task":"Image Classification","dataset":"RESISC45","model":"CLIP (ViT-B/16)","rank_in_archive_order":12,"of":20,"metrics":{"Top 1 Accuracy":"92.7"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-resisc45","task":"Image Classification","dataset":"RESISC45","model":"DeiT-B/16","rank_in_archive_order":14,"of":20,"metrics":{"Top 1 Accuracy":"92.48"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-resisc45","task":"Image Classification","dataset":"RESISC45","model":"SimCLR-v2 (ResNet152-w3 + SK)","rank_in_archive_order":15,"of":20,"metrics":{"Top 1 Accuracy":"89.77"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-resisc45","task":"Image Classification","dataset":"RESISC45","model":"ResNet50 (ImageNet-supervised)","rank_in_archive_order":16,"of":20,"metrics":{"Top 1 Accuracy":"88.56"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-resisc45","task":"Image Classification","dataset":"RESISC45","model":"MoCo-v2 (ResNet50)","rank_in_archive_order":18,"of":20,"metrics":{"Top 1 Accuracy":"85.4"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"SEER (RegNet10B)","rank_in_archive_order":12,"of":117,"metrics":{"PARAMS":"10000M","Percentage correct":"97.3"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-svhn","task":"Image Classification","dataset":"SVHN","model":"SEER (RegNet10B)","rank_in_archive_order":47,"of":62,"metrics":{"Percentage error":"13.6"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"SEER (RegNet10B - finetuned - 384px)","rank_in_archive_order":9,"of":60,"metrics":{"Top-1 Accuracy":"84.7%"},"uses_additional_data":true},{"leaderboard":"/sota/meme-classification-on-hateful-memes","task":"Meme Classification","dataset":"Hateful Memes","model":"SEER (RegNet10B)","rank_in_archive_order":15,"of":17,"metrics":{"ROC-AUC":"0.734"},"uses_additional_data":true},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"SEERv2","rank_in_archive_order":29,"of":144,"metrics":{"Number of Params":"10000M","Top 1 Accuracy":"79.8%"},"uses_additional_data":true},{"leaderboard":"/sota/self-supervised-image-classification-on-1","task":"Self-Supervised Image Classification","dataset":"ImageNet (finetuned)","model":"SEER (Regnet10B)","rank_in_archive_order":20,"of":65,"metrics":{"Number of Params":"10000M","Top 1 Accuracy":"85.8%"},"uses_additional_data":true},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"SEER (RegNet10B)","rank_in_archive_order":35,"of":65,"metrics":{"Top 1 Accuracy":"62.4%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"SEER (RegNet10B)","rank_in_archive_order":15,"of":75,"metrics":{"Top 1 Accuracy":"78.8%"},"uses_additional_data":true},{"leaderboard":"/sota/traffic-sign-recognition-on-gtsrb","task":"Traffic Sign Recognition","dataset":"GTSRB","model":"SEER (RegNet10B)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"90.71%"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.08360","atlas_url":"https://app.syntology.ai/?focus=2202.08360","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":"2202.08360"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2202.08360\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2202.08360"},"call":"get_concepts_for_paper(arxiv_id=\"2202.08360\")"}],"by_repo":[{"repo":"facebookresearch/vissl","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1603.09246","1803.07728","2106.08254","2202.07603"],"harvested_for_calls":[{"arxiv_id":"1603.09246","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1603.09246"},"call":"get_harvested_code_for_paper(arxiv_id=\"1603.09246\")"},{"arxiv_id":"1803.07728","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1803.07728"},"call":"get_harvested_code_for_paper(arxiv_id=\"1803.07728\")"},{"arxiv_id":"2106.08254","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.08254"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.08254\")"},{"arxiv_id":"2202.07603","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2202.07603"},"call":"get_harvested_code_for_paper(arxiv_id=\"2202.07603\")"}]}],"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":"f5f079e4c17cb6ec4cda008a20975d35b4834e0e921d4814a2b2678db06c6778","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}