[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-137723-105":59,"doc-detail-137723-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","bigdatasetgan-synthesizing-imagenet-with-pixel-wise-annotations-cvpr-2022","BigDatasetGAN - Synthesizing ImageNet with Pixel-wise Annotations - CVPR 2022","","Pixel-wise image annotation is expensive and slow, motivating dataset synthesis as an alternative to manual labeling. BigDatasetGAN scales the DatasetGAN idea to ImageNet scale by using a class-conditional BigGAN trained on ImageNet and manually labeling only 5 images per class across all 1,000 classes. A learned feature segmentation architecture turns BigGAN (and similarly VQGAN) into a generator of labeled data. The work builds a new ImageNet segmentation benchmark, conducts ablations, and shows gains for supervised and self-supervised pixel-wise training and downstream detection and segmentation.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/bigdatasetgan-synthesizing-imagenet-with-pixel-wise-annotations-cvpr-2022/137723/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/bigdatasetgan-synthesizing-imagenet-with-pixel-wise-annotations-cvpr-2022/137723.png","ImageObject",300,407,{"name":92,"@type":93},"Terk","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-17","2026-08-22",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does BigDatasetGAN address?","Question",{"text":112,"@type":113},"Pixel-wise labeling for large datasets is costly and time-consuming. BigDatasetGAN synthesizes high-quality labeled data to reduce manual annotation effort.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does BigDatasetGAN generate pixel-wise annotations?",{"text":117,"@type":113},"It samples images per class from BigGAN (and can leverage VQGAN), then manually labels only a small set of images per class and trains a feature segmentation branch to interpret GAN features.",{"name":119,"@type":110,"acceptedAnswer":120},"What evidence is provided for effectiveness?",{"text":121,"@type":113},"The paper builds a new ImageNet pixel-wise benchmark, evaluates multiple segmentation and dense prediction settings, and performs extensive ablation studies showing performance gains for supervised and self-supervised backbones.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},137723,1787438988,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144,"preview_page_count":4},1099525198933,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations  \nDaiqing Li 1 Karsten Kreis 1  \nHuan Ling 1 ,2 ,3 Sanja Fidler1 ,2 ,3  \nSeung Wook Kim 1 ,2 ,3 Antonio Torralba4  \n1NVIDIA 2University of Toronto 3Vector Institute 4MIT {daiqingl,huling,seungwookk,kkreis,[sfidler](sfidler}@nvidia.com)[}](sfidler}@nvidia.com)[@nvidia.com](sfidler}@nvidia.com) , [torralba@mit.edu](torralba@mit.edu)  \nFigure 1 . Our synthesized pixel-wise labeled ImageNet dataset. We sample both images and masks for each of the 1k ImageNet classes.  \nAbstract  \nAnnotating images with pixel-wise labels is a timeconsuming and costly process. Recently, DatasetGAN [78] showcased a promising alternative – to synthesize a large labeled dataset via a generative adversarial network (GAN) by exploiting a small set of manually labeled, GANgenerated images. Here, we scale DatasetGAN to ImageNet scale of class diversity. We take image samples from the class-conditional generative model BigGAN [5] trained on ImageNet, and manually annotate only 5 images per class, for all 1k classes. By training an effective feature segmentation architecture on top of BigGAN, we turn BigGAN into a labeled dataset generator. We further show that VQGAN [18] can similarly serve as a dataset generator, leveraging the already annotated data. We create a new ImageNet benchmark by labeling an additional set of real images and evaluate segmentation performance in a variety of settings. Through an extensive ablation study, we show big gains in leveraging a large generated dataset to train different supervised and self-supervised backbone modelson pixel-wise tasks. Furthermore, we demonstrate that using our synthesized datasets for pre-training leads to improvements over standard ImageNet pre-training on several downstream datasets, such as PASCAL-VOC, MS-COCO, Cityscapes and chest X-ray, as well as tasks (detection, segmentation). Our benchmark will be made public and maintain a leaderboard for this challenging task. Project Page:  \n[https://nv-tlabs.github.io/big-datasetgan/](https://nv-tlabs.github.io/big-datasetgan/)  \n1. Introduction  \nThe ImageNet dataset [65] has served as a cornerstone of modern computer vision and deep learning. It is used asa testbed for innovating in the domain of large-scale classification, and has enabled incredible advancements over the years [15, 29, 42, 67] . Importantly, it has also been com-  \nmonly used for pre-training backbone models, with either supervised or recently self-supervised pre-training, leading to almost guaranteed performance gains on a plethora of downstream datasets and tasks [24, 77] . ImageNet contains a million images with 1000-way classification labels. This huge class diversity is what makes pre-trained networks generalize well to a variety of downstream applications.  \nIn this paper, we aim to enhance ImageNet with pixelwise labels, to enable large-scale multi-class segmentation challenges and offer opportunities for new pre-training strategies for dense downstream prediction tasks. However, instead of manually labeling masks for 1M images, which is time-consuming and costly, we instead synthesize high quality labeled data at a fraction of the cost.  \nWe build on top of DatasetGAN [78], which introduced a simple idea: to manually annotate a very small set of GANgenerated images with pixel-wise labels, and add a shallow segmentation branch on top of the GAN’s feature maps, which is trained on this small dataset. It was shown that the generator’s feature maps are incredibly powerful and semantically meaningful, and allow the segmentation branch to produce very accurate labels for new random samples from the GAN. This means that the GAN is successfully re-purposed as a dataset generator, producing samples in the form of images and their pixel-wise labels. The authors showed that synthesizing a large dataset and using it to train downstream segmentation networks leads to extremely high performance at only a fraction of the labeling c","cbCaiu4LFk7jUXdK","https://ap.wps.com/l/cbCaiu4LFk7jUXdK","pdf",9563257,11,"English","# Introduction\n## Motivation: ImageNet and dense prediction\n## DatasetGAN foundation and limitations\n## Contributions of BigDatasetGAN\n# Benchmark construction and evaluation","[{\"question\":\"What problem does BigDatasetGAN address?\",\"answer\":\"Pixel-wise labeling for large datasets is costly and time-consuming. BigDatasetGAN synthesizes high-quality labeled data to reduce manual annotation effort.\"},{\"question\":\"How does BigDatasetGAN generate pixel-wise annotations?\",\"answer\":\"It samples images per class from BigGAN (and can leverage VQGAN), then manually labels only a small set of images per class and trains a feature segmentation branch to interpret GAN features.\"},{\"question\":\"What evidence is provided for effectiveness?\",\"answer\":\"The paper builds a new ImageNet pixel-wise benchmark, evaluates multiple segmentation and dense prediction settings, and performs extensive ablation studies showing performance gains for supervised and self-supervised backbones.\"}]","BigDatasetGAN - Synthesizing ImageNet with Pixel-wise Annotations - CVPR 2022 | PDF",28]