{"url":"/sota/conditional-image-generation-on-cifar-10","task":{"name":"Conditional Image Generation","url":"/task/conditional-image-generation","note":null},"dataset":{"name":"CIFAR-10","url":"/dataset/cifar-10"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Conditional image generation is the task of generating new images from a dataset conditional on their class.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [PixelCNN++](https://github.com/openai/pixel-cnn) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["FID","Inception score","Intra-FID"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"FID":"lower","Inception score":"higher","Intra-FID":"lower"}},"counts":{"rows":25,"rows_with_code":24,"rows_with_paper_page":25,"rows_dated":25,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"EDM-G++ (conditional)","metrics":{"FID":"1.64"},"uses_additional_data":false,"paper_date":"2022-11-28","paper":"/paper/refining-generative-process-with","paper_url":"https://arxiv.org/abs/2211.17091v4","paper_title":"Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models","code":"https://github.com/alsdudrla10/DG","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":2,"model":"DLSM","metrics":{"FID":"2.25","Inception score":"9.90"},"uses_additional_data":false,"paper_date":"2022-03-27","paper":"/paper/denoising-likelihood-score-matching-for-1","paper_url":"https://arxiv.org/abs/2203.14206v1","paper_title":"Denoising Likelihood Score Matching for Conditional Score-based Data Generation","code":"https://github.com/chen-hao-chao/dlsm","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"StyleGAN2 + DiffAugment + D2D-CE","metrics":{"FID":"2.26","Inception score":"10.51"},"uses_additional_data":false,"paper_date":"2021-11-01","paper":"/paper/rebooting-acgan-auxiliary-classifier-gans","paper_url":"https://arxiv.org/abs/2111.01118v1","paper_title":"Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training","code":"https://github.com/POSTECH-CVLab/PyTorch-StudioGAN","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":0,"n_samples":9,"n_pointer_only_licence":9}},{"rank_in_archive_order":4,"model":"StyleGAN2-ADA","metrics":{"FID":"2.42","Inception score":"10.14"},"uses_additional_data":false,"paper_date":"2020-06-11","paper":"/paper/training-generative-adversarial-networks-with-2","paper_url":"https://arxiv.org/abs/2006.06676v2","paper_title":"Training Generative Adversarial Networks with Limited Data","code":"https://github.com/NVlabs/stylegan2-ada-pytorch","n_code_links":28,"syntology":{"n_ran":5,"n_unverified":24,"n_samples":29,"n_pointer_only_licence":4}},{"rank_in_archive_order":5,"model":"MIX-MHingeGAN","metrics":{"FID":"3.6","Inception score":"10.21"},"uses_additional_data":false,"paper_date":"2020-07-13","paper":"/paper/lessons-learned-from-the-training-of-gans-on","paper_url":"https://arxiv.org/abs/2007.06418v2","paper_title":"Lessons Learned from the Training of GANs on Artificial Datasets","code":"https://github.com/tsc2017/MIX-GAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"FQ-GAN","metrics":{"FID":"5.34","Inception score":"8.50"},"uses_additional_data":false,"paper_date":"2020-04-05","paper":"/paper/feature-quantization-improves-gan-training","paper_url":"https://arxiv.org/abs/2004.02088v2","paper_title":"Feature Quantization Improves GAN Training","code":"https://github.com/YangNaruto/FQ-GAN","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"ADC-GAN","metrics":{"FID":"5.66","Intra-FID":"40.45"},"uses_additional_data":false,"paper_date":"2021-07-21","paper":"/paper/cgans-with-auxiliary-discriminative","paper_url":"https://arxiv.org/abs/2107.10060v5","paper_title":"Conditional GANs with Auxiliary Discriminative Classifier","code":"https://github.com/POSTECH-CVLab/PyTorch-StudioGAN","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":8,"model":"aw-BigGAN","metrics":{"FID":"6.89","Inception score":"9.52"},"uses_additional_data":false,"paper_date":"2020-12-05","paper":"/paper/adaptive-weighted-discriminator-for-training","paper_url":"https://arxiv.org/abs/2012.03149v2","paper_title":"Adaptive Weighted Discriminator for Training Generative Adversarial Networks","code":"https://github.com/vasily789/adaptive-weighted-gans","n_code_links":3,"syntology":null},{"rank_in_archive_order":9,"model":"MHingeGAN","metrics":{"FID":"7.5","Inception score":"9.58"},"uses_additional_data":false,"paper_date":"2019-12-09","paper":"/paper/cgans-with-multi-hinge-loss","paper_url":"https://arxiv.org/abs/1912.04216v2","paper_title":"cGANs with Multi-Hinge Loss","code":"https://github.com/ilyakava/BigGAN-PyTorch","n_code_links":3,"syntology":null},{"rank_in_archive_order":10,"model":"aw-SN-GAN","metrics":{"FID":"8.03","Inception score":"9"},"uses_additional_data":false,"paper_date":"2020-12-05","paper":"/paper/adaptive-weighted-discriminator-for-training","paper_url":"https://arxiv.org/abs/2012.03149v2","paper_title":"Adaptive Weighted Discriminator for Training Generative Adversarial Networks","code":"https://github.com/vasily789/adaptive-weighted-gans","n_code_links":3,"syntology":null},{"rank_in_archive_order":11,"model":"NDA","metrics":{"FID":"9.42"},"uses_additional_data":false,"paper_date":"2021-02-09","paper":"/paper/negative-data-augmentation-1","paper_url":"https://arxiv.org/abs/2102.05113v1","paper_title":"Negative Data Augmentation","code":"https://github.com/ermongroup/NDA","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":12,"model":"ContraGAN","metrics":{"FID":"10.30"},"uses_additional_data":false,"paper_date":"2020-06-23","paper":"/paper/contrastive-generative-adversarial-networks","paper_url":"https://arxiv.org/abs/2006.12681v3","paper_title":"ContraGAN: Contrastive Learning for Conditional Image Generation","code":"https://github.com/POSTECH-CVLab/PyTorch-StudioGAN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":13,"model":"CR-BigGAN","metrics":{"FID":"11.67"},"uses_additional_data":false,"paper_date":"2019-10-26","paper":"/paper/consistency-regularization-for-generative-1","paper_url":"https://arxiv.org/abs/1910.12027v2","paper_title":"Consistency Regularization for Generative Adversarial Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"BigGAN","metrics":{"FID":"14.73","Inception score":"9.22"},"uses_additional_data":false,"paper_date":"2018-09-28","paper":"/paper/large-scale-gan-training-for-high-fidelity","paper_url":"http://arxiv.org/abs/1809.11096v2","paper_title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","code":"https://github.com/ajbrock/BigGAN-PyTorch","n_code_links":35,"syntology":{"n_ran":14,"n_unverified":27,"n_samples":41,"n_pointer_only_licence":4}},{"rank_in_archive_order":15,"model":"Projection Discriminator","metrics":{"FID":"17.5","Inception score":"8.62"},"uses_additional_data":false,"paper_date":"2018-02-15","paper":"/paper/cgans-with-projection-discriminator","paper_url":"http://arxiv.org/abs/1802.05637v2","paper_title":"cGANs with Projection Discriminator","code":"https://github.com/pfnet-research/sngan_projection","n_code_links":12,"syntology":{"n_ran":9,"n_unverified":0,"n_samples":9,"n_pointer_only_licence":6}},{"rank_in_archive_order":16,"model":"ProdPoly no activation functions","metrics":{"FID":"36.77","Inception score":"7.5"},"uses_additional_data":false,"paper_date":"2020-06-20","paper":"/paper/deep-polynomial-neural-networks","paper_url":"https://arxiv.org/abs/2006.13026v2","paper_title":"Deep Polynomial Neural Networks","code":"https://github.com/Faceplugin-ltd/FaceRecognition-Android","n_code_links":5,"syntology":null},{"rank_in_archive_order":17,"model":"Splitting GAN","metrics":{"Inception score":"8.87"},"uses_additional_data":false,"paper_date":"2017-09-21","paper":"/paper/class-splitting-generative-adversarial","paper_url":"http://arxiv.org/abs/1709.07359v2","paper_title":"Class-Splitting Generative Adversarial Networks","code":"https://github.com/CIFASIS/splitting_gan","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"WGAN-GP","metrics":{"Inception score":"8.67"},"uses_additional_data":false,"paper_date":"2017-03-31","paper":"/paper/improved-training-of-wasserstein-gans","paper_url":"http://arxiv.org/abs/1704.00028v3","paper_title":"Improved Training of Wasserstein GANs","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":110,"syntology":{"n_ran":27,"n_unverified":22,"n_samples":49,"n_pointer_only_licence":20}},{"rank_in_archive_order":19,"model":"SGAN","metrics":{"Inception score":"8.59"},"uses_additional_data":false,"paper_date":"2016-12-13","paper":"/paper/stacked-generative-adversarial-networks","paper_url":"http://arxiv.org/abs/1612.04357v4","paper_title":"Stacked Generative Adversarial Networks","code":"https://github.com/xunhuang1995/SGAN","n_code_links":2,"syntology":null},{"rank_in_archive_order":20,"model":"AC-GAN","metrics":{"Inception score":"8.25"},"uses_additional_data":false,"paper_date":"2016-10-30","paper":"/paper/conditional-image-synthesis-with-auxiliary","paper_url":"http://arxiv.org/abs/1610.09585v4","paper_title":"Conditional Image Synthesis With Auxiliary Classifier GANs","code":"https://github.com/eriklindernoren/PyTorch-GAN","n_code_links":37,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":21,"model":"Improved GAN","metrics":{"Inception score":"8.09"},"uses_additional_data":false,"paper_date":"2016-06-10","paper":"/paper/improved-techniques-for-training-gans","paper_url":"http://arxiv.org/abs/1606.03498v1","paper_title":"Improved Techniques for Training GANs","code":"https://github.com/tensorflow/models/tree/master/research/gan","n_code_links":46,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"LR-GAN","metrics":{"Inception score":"7.17"},"uses_additional_data":false,"paper_date":"2017-03-05","paper":"/paper/lr-gan-layered-recursive-generative","paper_url":"http://arxiv.org/abs/1703.01560v3","paper_title":"LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation","code":"https://github.com/jwyang/lr-gan.pytorch","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"EGAN-Ent-VI","metrics":{"Inception score":"7.07"},"uses_additional_data":false,"paper_date":"2017-02-06","paper":"/paper/calibrating-energy-based-generative","paper_url":"http://arxiv.org/abs/1702.01691v2","paper_title":"Calibrating Energy-based Generative Adversarial Networks","code":"https://github.com/zihangdai/cegan_iclr2017","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"DCGAN","metrics":{"Inception score":"6.58"},"uses_additional_data":false,"paper_date":"2015-11-19","paper":"/paper/unsupervised-representation-learning-with-1","paper_url":"http://arxiv.org/abs/1511.06434v2","paper_title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","code":"https://github.com/tensorflow/models/blob/master/research/slim/nets/dcgan.py","n_code_links":258,"syntology":{"n_ran":113,"n_unverified":106,"n_samples":219,"n_pointer_only_licence":111}},{"rank_in_archive_order":25,"model":"SteinGAN","metrics":{"Inception score":"6.35"},"uses_additional_data":false,"paper_date":"2016-11-06","paper":"/paper/learning-to-draw-samples-with-application-to","paper_url":"http://arxiv.org/abs/1611.01722v2","paper_title":"Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning","code":"https://github.com/DartML/SteinGAN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":15,"rows_with_any_sample_ran":14,"distinct_papers_with_graph_line":15,"distinct_papers_with_any_sample_ran":14,"samples_over_distinct_papers":{"n_ran":195,"n_unverified":189,"n_samples":384,"n_pointer_only_licence":171,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":195,"n_unverified":189,"n_samples":384,"n_pointer_only_licence":171,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}