{"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/revisiting-weakly-supervised-pre-training-of","title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","arxiv_id":"2201.08371","date":"2022-01-20","proceeding":"CVPR 2022 1","authors":["Mannat Singh","Laura Gustafson","Aaron Adcock","Vinicius de Freitas Reis","Bugra Gedik","Raj Prateek Kosaraju","Dhruv Mahajan","Ross Girshick","Piotr Dollár","Laurens van der Maaten"],"abstract":"Model pre-training is a cornerstone of modern visual recognition systems. Although fully supervised pre-training on datasets like ImageNet is still the de-facto standard, recent studies suggest that large-scale weakly supervised pre-training can outperform fully supervised approaches. This paper revisits weakly-supervised pre-training of models using hashtag supervision with modern versions of residual networks and the largest-ever dataset of images and corresponding hashtags. We study the performance of the resulting models in various transfer-learning settings including zero-shot transfer. We also compare our models with those obtained via large-scale self-supervised learning. We find our weakly-supervised models to be very competitive across all settings, and find they substantially outperform their self-supervised counterparts. We also include an investigation into whether our models learned potentially troubling associations or stereotypes. Overall, our results provide a compelling argument for the use of weakly supervised learning in the development of visual recognition systems. Our models, Supervised Weakly through hashtAGs (SWAG), are available publicly.","url_abs":"https://arxiv.org/abs/2201.08371v2","url_pdf":"https://arxiv.org/pdf/2201.08371v2.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":"revisiting-weakly-supervised-pre-training-of","repo_url":"https://github.com/facebookresearch/SWAG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"revisiting-weakly-supervised-pre-training-of","repo_url":"https://github.com/Expedit-LargeScale-Vision-Transformer/Expedit-SWAG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-cub-200-1","task":"Fine-Grained Image Classification","dataset":"CUB-200-2011","model":"SWAG (ViT H/14)","rank_in_archive_order":8,"of":30,"metrics":{"Accuracy":"91.7"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SWAG (ViT H/14)","rank_in_archive_order":38,"of":1060,"metrics":{"GFLOPs":"1018.8","Number of params":"633.5M","Top 1 Accuracy":"88.6%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet-real","task":"Image Classification","dataset":"ImageNet ReaL","model":"SWAG (RegNetY 128GF)","rank_in_archive_order":13,"of":57,"metrics":{"Accuracy":"90.7%"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet-v2","task":"Image Classification","dataset":"ImageNet V2","model":"SWAG (ViT H/14)","rank_in_archive_order":9,"of":33,"metrics":{"Top 1 Accuracy":"81.1"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"SWAG (ViT H/14)","rank_in_archive_order":15,"of":106,"metrics":{"Top-1 Accuracy":"69.5"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"RegNetY 128GF (Platt)","rank_in_archive_order":17,"of":106,"metrics":{"Top-1 Accuracy":"64.3"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"ViT H/14 (Platt)","rank_in_archive_order":20,"of":106,"metrics":{"Top-1 Accuracy":"60"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"ViT L/16 (Platt)","rank_in_archive_order":22,"of":106,"metrics":{"Top-1 Accuracy":"57.3"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"ViT B/16","rank_in_archive_order":29,"of":106,"metrics":{"Top-1 Accuracy":"48.9"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-places365-standard","task":"Image Classification","dataset":"Places365-Standard","model":"SWAG (ViT H/14)","rank_in_archive_order":1,"of":4,"metrics":{"Top 1 Accuracy":"60.7"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"SWAG (ViT H/14)","rank_in_archive_order":8,"of":60,"metrics":{"Top-1 Accuracy":"86.0%"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2201.08371","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}