{"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/instance-conditioned-gan","title":"Instance-Conditioned GAN","arxiv_id":"2109.05070","date":"2021-09-10","proceeding":"NeurIPS 2021 12","authors":["Arantxa Casanova","Marlène Careil","Jakob Verbeek","Michal Drozdzal","Adriana Romero-Soriano"],"abstract":"Generative Adversarial Networks (GANs) can generate near photo realistic images in narrow domains such as human faces. Yet, modeling complex distributions of datasets such as ImageNet and COCO-Stuff remains challenging in unconditional settings. In this paper, we take inspiration from kernel density estimation techniques and introduce a non-parametric approach to modeling distributions of complex datasets. We partition the data manifold into a mixture of overlapping neighborhoods described by a datapoint and its nearest neighbors, and introduce a model, called instance-conditioned GAN (IC-GAN), which learns the distribution around each datapoint. Experimental results on ImageNet and COCO-Stuff show that IC-GAN significantly improves over unconditional models and unsupervised data partitioning baselines. Moreover, we show that IC-GAN can effortlessly transfer to datasets not seen during training by simply changing the conditioning instances, and still generate realistic images. Finally, we extend IC-GAN to the class-conditional case and show semantically controllable generation and competitive quantitative results on ImageNet; while improving over BigGAN on ImageNet-LT. Code and trained models to reproduce the reported results are available at https://github.com/facebookresearch/ic_gan.","url_abs":"https://arxiv.org/abs/2109.05070v2","url_pdf":"https://arxiv.org/pdf/2109.05070v2.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":"instance-conditioned-gan","repo_url":"https://github.com/facebookresearch/ic_gan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"unconditional-image-generation","task_name":"Unconditional Image Generation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"conditional-batch-normalization","method_name":"Conditional Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"early-stopping","method_name":"Early Stopping"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"gan-hinge-loss","method_name":"GAN Hinge Loss"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"non-local-block","method_name":"Non-Local Block"},{"method_slug":"non-local-operation","method_name":"Non-Local Operation"},{"method_slug":"off-diagonal-orthogonal-regularization","method_name":"Off-Diagonal Orthogonal Regularization"},{"method_slug":"projection-discriminator","method_name":"Projection Discriminator"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sagan","method_name":"SAGAN"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spectral-normalization","method_name":"Spectral Normalization"},{"method_slug":"ttur","method_name":"TTUR"},{"method_slug":"truncation-trick","method_name":"Truncation Trick"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/conditional-image-generation-on-imagenet","task":"Conditional Image Generation","dataset":"ImageNet 128x128","model":"IC-GAN + DA","rank_in_archive_order":15,"of":22,"metrics":{"FID":"9.5","Inception score":"108.6"},"uses_additional_data":false},{"leaderboard":"/sota/conditional-image-generation-on-imagenet-2","task":"Conditional Image Generation","dataset":"ImageNet 256x256","model":"BigGAN+ [Brock et al.] (chx96)","rank_in_archive_order":4,"of":5,"metrics":{"FID":"8.1","Inception score":"144.2"},"uses_additional_data":false},{"leaderboard":"/sota/conditional-image-generation-on-imagenet-2","task":"Conditional Image Generation","dataset":"ImageNet 256x256","model":"IC-GAN (chx96) + DA","rank_in_archive_order":5,"of":5,"metrics":{"FID":"8.2±0.1","Inception score":"173.8±0.9"},"uses_additional_data":false},{"leaderboard":"/sota/conditional-image-generation-on-imagenet-1","task":"Conditional Image Generation","dataset":"ImageNet 64x64","model":"IC-GAN + DA","rank_in_archive_order":1,"of":4,"metrics":{"FID":"6.7","Inception score":"45.9±0.3"},"uses_additional_data":false},{"leaderboard":"/sota/conditional-image-generation-on-imagenet-1","task":"Conditional Image Generation","dataset":"ImageNet 64x64","model":"BigGAN* [Brock et al.] +DA","rank_in_archive_order":4,"of":4,"metrics":{"FID":"10.2±0.1","Inception score":"30.1±0.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.05070","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}