{"url":"/dataset/celeba","name":"CelebA","full_name":"CelebFaces Attributes Dataset","description_markdown":"CelebFaces Attributes dataset contains 202,599 face images of the size 178×218 from 10,177 celebrities, each annotated with 40 binary labels indicating facial attributes like hair color, gender and age.\r\n\r\nSource: [Show, Attend and Translate: Unpaired Multi-Domain Image-to-Image Translation with Visual Attention](https://arxiv.org/abs/1811.07483)\r\nImage Source: [http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html)","description_withheld":null,"homepage":"http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html","introduced_date":"2015-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/deep-learning-face-attributes-in-the-wild","title":"Deep Learning Face Attributes in the Wild","first_author":"Ziwei Liu","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"Image Super-Resolution","url":"/task/image-super-resolution","datasets_with_task":"/datasets/task/image-super-resolution"},{"name":"Face Alignment","url":"/task/face-alignment","datasets_with_task":"/datasets/task/face-alignment"},{"name":"Long-tail Learning","url":"/task/long-tail-learning","datasets_with_task":"/datasets/task/long-tail-learning"},{"name":"Image Inpainting","url":"/task/image-inpainting","datasets_with_task":"/datasets/task/image-inpainting"},{"name":"Multi-Task Learning","url":"/task/multi-task-learning","datasets_with_task":"/datasets/task/multi-task-learning"},{"name":"Image Deblurring","url":"/task/image-deblurring","datasets_with_task":"/datasets/task/image-deblurring"},{"name":"Image Compressed Sensing","url":"/task/image-compressed-sensing","datasets_with_task":"/datasets/task/image-compressed-sensing"},{"name":"Concept-based Classification","url":"/task/concept-based-classification","datasets_with_task":"/datasets/task/concept-based-classification"},{"name":"Blind Face Restoration","url":"/task/blind-face-restoration","datasets_with_task":"/datasets/task/blind-face-restoration"},{"name":"Facial Expression Translation","url":"/task/facial-expression-translation","datasets_with_task":"/datasets/task/facial-expression-translation"},{"name":"Image Colorization","url":"/task/image-colorization","datasets_with_task":"/datasets/task/image-colorization"},{"name":"Image Attribution","url":"/task/image-attribution","datasets_with_task":"/datasets/task/image-attribution"},{"name":"Interpretability Techniques for Deep Learning","url":"/task/interpretability-techniques-for-deep-learning","datasets_with_task":"/datasets/task/interpretability-techniques-for-deep-learning"},{"name":"Physical Attribute Prediction","url":"/task/physical-attribute-prediction","datasets_with_task":"/datasets/task/physical-attribute-prediction"},{"name":"HairColor/Unbiased","url":"/task/haircolor-unbiased","datasets_with_task":"/datasets/task/haircolor-unbiased"},{"name":"HairColor/Bias-conflicting","url":"/task/haircolor-bias-conflicting","datasets_with_task":"/datasets/task/haircolor-bias-conflicting"},{"name":"HeavyMakeup/Unbiased","url":"/task/heavymakeup-unbiased","datasets_with_task":"/datasets/task/heavymakeup-unbiased"},{"name":"HeavyMakeup/Bias-conflicting","url":"/task/heavymakeup-bias-conflicting","datasets_with_task":"/datasets/task/heavymakeup-bias-conflicting"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["CelebA-wild","CelebA Unaligned","CelebA-Test","CelebA-faces","CelebA-5","CelebA Aligned","CelebA 64x64","CelebA 256x256","CelebA 128 x 128","CelebA + AFLW Unaligned","CelebA 128x128","CelebA"],"data_loaders":[{"repo":"https://github.com/pytorch/vision","url":"https://pytorch.org/vision/stable/generated/torchvision.datasets.CelebA.html","frameworks":["pytorch"]},{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/celeba-dataset","frameworks":["tf","pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/celeb_a","frameworks":["tf","jax"]}],"num_papers_in_archive":3477,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-generation-on-celeba-64x64","task":"Image Generation","dataset_variant":"CelebA 64x64","rows":39,"metrics":["FID","bits/dimension","Precision","Recall","FID_CLIP","Model Size (MB)"],"first_row_in_archive_order":{"model":"DDPM-IP","paper":"/paper/input-perturbation-reduces-exposure-bias-in","metrics":{"FID":"1.27"},"code_links":[{"title":"forever208/ddpm-ip","url":"https://github.com/forever208/ddpm-ip"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-celeba-256x256","task":"Image Generation","dataset_variant":"CelebA 256x256","rows":17,"metrics":["bpd","FID","bpd (8-bits)"],"first_row_in_archive_order":{"model":"Efficient-VDVAE","paper":"/paper/efficient-vdvae-less-is-more","metrics":{"bpd":"0.51","bpd (8-bits)":"1.35"},"code_links":[{"title":"Rayhane-mamah/Efficient-VDVAE","url":"https://github.com/Rayhane-mamah/Efficient-VDVAE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/blind-face-restoration-on-celeba-test","task":"Blind Face Restoration","dataset_variant":"CelebA-Test","rows":15,"metrics":["LPIPS","FID","NIQE","Deg.","PSNR","SSIM","IDS"],"first_row_in_archive_order":{"model":"CodeFormer","paper":"/paper/towards-robust-blind-face-restoration-with","metrics":{"FID":"60.62","IDS":"60","LPIPS":"29.9","PSNR":"22.18","SSIM":"0.61"},"code_links":[{"title":"sczhou/codeformer","url":"https://github.com/sczhou/codeformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-attribution-on-celeba","task":"Image Attribution","dataset_variant":"CelebA","rows":8,"metrics":["Insertion AUC score (ArcFace ResNet-101)","Deletion AUC score (ArcFace ResNet-101)"],"first_row_in_archive_order":{"model":"SMDL-Attribution (ICLR version)","paper":"/paper/less-is-more-fewer-interpretable-region-via","metrics":{"Deletion AUC score (ArcFace ResNet-101)":"0.1054","Insertion AUC score (ArcFace ResNet-101)":"0.5752"},"code_links":[{"title":"ruoyuchen10/smdl-attribution","url":"https://github.com/ruoyuchen10/smdl-attribution"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/interpretability-techniques-for-deep-learning-1","task":"Interpretability Techniques for Deep Learning","dataset_variant":"CelebA","rows":7,"metrics":["Insertion AUC score"],"first_row_in_archive_order":{"model":"RISE","paper":"/paper/rise-randomized-input-sampling-for","metrics":{"Insertion AUC score":"0.5703"},"code_links":[{"title":"openvinotoolkit/datumaro","url":"https://github.com/openvinotoolkit/datumaro"},{"title":"eclique/RISE","url":"https://github.com/eclique/RISE"},{"title":"dbash/zerowaste","url":"https://github.com/dbash/zerowaste"},{"title":"hysts/pytorch_D-RISE","url":"https://github.com/hysts/pytorch_D-RISE"},{"title":"openvinotoolkit/openvino_xai","url":"https://github.com/openvinotoolkit/openvino_xai"},{"title":"yiskw713/RISE","url":"https://github.com/yiskw713/RISE"},{"title":"wickstrom/relax","url":"https://github.com/wickstrom/relax"},{"title":"tristangomez44/metrics-saliency-maps","url":"https://github.com/tristangomez44/metrics-saliency-maps"},{"title":"vlue-c/Visual-Explanation-Methods-PyTorch","url":"https://github.com/vlue-c/Visual-Explanation-Methods-PyTorch"},{"title":"myurasov/RISE","url":"https://github.com/myurasov/RISE"},{"title":"vlue-c/PyTorch-Explanations","url":"https://github.com/vlue-c/PyTorch-Explanations"},{"title":"palatos/RISE_tf","url":"https://github.com/palatos/RISE_tf"},{"title":"ftorres11/saliencysense","url":"https://github.com/ftorres11/saliencysense"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-celeba-128x128","task":"Image Generation","dataset_variant":"CelebA 128x128","rows":5,"metrics":["FID","Inception score","MS-SSIM"],"first_row_in_archive_order":{"model":"U-Net GAN","paper":"/paper/a-u-net-based-discriminator-for-generative","metrics":{"FID":"2.95","Inception score":"3.43"},"code_links":[{"title":"boschresearch/unetgan","url":"https://github.com/boschresearch/unetgan"},{"title":"xingchenzhao/Generating-Human-Skeletons-with-Mutual-Actions-WGAN-Pytorch","url":"https://github.com/xingchenzhao/Generating-Human-Skeletons-with-Mutual-Actions-WGAN-Pytorch"},{"title":"xingchenzhao/deep-learning-team-project","url":"https://github.com/xingchenzhao/deep-learning-team-project"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-inpainting-on-celeba","task":"Image Inpainting","dataset_variant":"CelebA","rows":5,"metrics":["FID","PSNR","SSIM","LPIPS"],"first_row_in_archive_order":{"model":"DDNM","paper":"/paper/zero-shot-image-restoration-using-denoising","metrics":{"FID":"4.54","PSNR":"35.64","SSIM":"0.982"},"code_links":[{"title":"wyhuai/ddnm","url":"https://github.com/wyhuai/ddnm"},{"title":"xypeng9903/k-diffusion-inverse-problems","url":"https://github.com/xypeng9903/k-diffusion-inverse-problems"},{"title":"ipc-lab/deepjscc-diffusion","url":"https://github.com/ipc-lab/deepjscc-diffusion"},{"title":"andreamazzitelli/ProjectNN","url":"https://github.com/andreamazzitelli/ProjectNN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-super-resolution-on-celeba","task":"Image Super-Resolution","dataset_variant":"CelebA","rows":5,"metrics":["FID","PSNR","SSIM"],"first_row_in_archive_order":{"model":"DDNM","paper":"/paper/zero-shot-image-restoration-using-denoising","metrics":{"FID":"22.27","PSNR":"31.63","SSIM":"0.945"},"code_links":[{"title":"wyhuai/ddnm","url":"https://github.com/wyhuai/ddnm"},{"title":"xypeng9903/k-diffusion-inverse-problems","url":"https://github.com/xypeng9903/k-diffusion-inverse-problems"},{"title":"ipc-lab/deepjscc-diffusion","url":"https://github.com/ipc-lab/deepjscc-diffusion"},{"title":"andreamazzitelli/ProjectNN","url":"https://github.com/andreamazzitelli/ProjectNN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-classification-on-celeba-64x64","task":"Image Classification","dataset_variant":"CelebA 64x64","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"cFlow","paper":"/paper/null-sampling-for-interpretable-and-fair","metrics":{"Accuracy":"0.82"},"code_links":[{"title":"predictive-analytics-lab/nifr","url":"https://github.com/predictive-analytics-lab/nifr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-colorization-on-celeba","task":"Image Colorization","dataset_variant":"CelebA","rows":3,"metrics":["Consistency","FID"],"first_row_in_archive_order":{"model":"DDRM","paper":"/paper/zero-shot-image-restoration-using-denoising","metrics":{"Consistency":"455.9","FID":"31.26"},"code_links":[{"title":"wyhuai/ddnm","url":"https://github.com/wyhuai/ddnm"},{"title":"xypeng9903/k-diffusion-inverse-problems","url":"https://github.com/xypeng9903/k-diffusion-inverse-problems"},{"title":"ipc-lab/deepjscc-diffusion","url":"https://github.com/ipc-lab/deepjscc-diffusion"},{"title":"andreamazzitelli/ProjectNN","url":"https://github.com/andreamazzitelli/ProjectNN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-deblurring-on-celeba","task":"Image Deblurring","dataset_variant":"CelebA","rows":3,"metrics":["FID","PSNR","SSIM"],"first_row_in_archive_order":{"model":"DDNM","paper":"/paper/zero-shot-image-restoration-using-denoising","metrics":{"FID":"1.41","PSNR":"46.72","SSIM":"0.996"},"code_links":[{"title":"wyhuai/ddnm","url":"https://github.com/wyhuai/ddnm"},{"title":"xypeng9903/k-diffusion-inverse-problems","url":"https://github.com/xypeng9903/k-diffusion-inverse-problems"},{"title":"ipc-lab/deepjscc-diffusion","url":"https://github.com/ipc-lab/deepjscc-diffusion"},{"title":"andreamazzitelli/ProjectNN","url":"https://github.com/andreamazzitelli/ProjectNN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/concept-based-classification-on-celeba","task":"Concept-based Classification","dataset_variant":"CelebA","rows":2,"metrics":["Task Accuracy (%)","Concept Accuracy (%)"],"first_row_in_archive_order":{"model":"EQ-CBM (ResNet-34)","paper":"/paper/eq-cbm-a-probabilistic-concept-bottleneck-1","metrics":{"Concept Accuracy (%)":"90.617","Task Accuracy (%)":"56.600"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/face-alignment-on-celeba-aflw-unaligned","task":"Face Alignment","dataset_variant":"CelebA + AFLW Unaligned","rows":1,"metrics":["MOS","MS-SSIM","PSNR","SSIM"],"first_row_in_archive_order":{"model":"Progressive Face SR","paper":"/paper/progressive-face-super-resolution-via","metrics":{"MOS":"3.73","MS-SSIM":"0.897","PSNR":"22.96","SSIM":"0.695"},"code_links":[{"title":"DeokyunKim/Progressive-Face-Super-Resolution","url":"https://github.com/DeokyunKim/Progressive-Face-Super-Resolution"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/face-alignment-on-celeba-aligned","task":"Face Alignment","dataset_variant":"CelebA Aligned","rows":1,"metrics":["MOS","MS-SSIM","PSNR","SSIM"],"first_row_in_archive_order":{"model":"Progressive Face SR","paper":"/paper/progressive-face-super-resolution-via","metrics":{"MOS":"3.73","MS-SSIM":"0.902","PSNR":"22.66","SSIM":"0.685"},"code_links":[{"title":"DeokyunKim/Progressive-Face-Super-Resolution","url":"https://github.com/DeokyunKim/Progressive-Face-Super-Resolution"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-celeba-3","task":"Image Generation","dataset_variant":"CelebA","rows":1,"metrics":["bpd (8-bits)"],"first_row_in_archive_order":{"model":"FInCFlow","paper":"/paper/finc-flow-fast-and-invertible-k-times-k","metrics":{"bpd (8-bits)":"NaN"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/long-tail-learning-on-celeba-5","task":"Long-tail Learning","dataset_variant":"CelebA-5","rows":1,"metrics":["Error Rate"],"first_row_in_archive_order":{"model":"OPeN (WideResNet-28-10)","paper":"/paper/pure-noise-to-the-rescue-of-insufficient-data","metrics":{"Error Rate":"19.1"},"code_links":[{"title":"shiranzada/pure-noise","url":"https://github.com/shiranzada/pure-noise"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-task-learning-on-celeba","task":"Multi-Task Learning","dataset_variant":"CelebA","rows":1,"metrics":["Error"],"first_row_in_archive_order":{"model":"MGDA-UB","paper":"/paper/multi-task-learning-as-multi-objective","metrics":{"Error":"8.25"},"code_links":[{"title":"IntelVCL/MultiObjectiveOptimization","url":"https://github.com/IntelVCL/MultiObjectiveOptimization"},{"title":"isl-org/multiobjectiveoptimization","url":"https://github.com/isl-org/multiobjectiveoptimization"},{"title":"ebagdasa/backdoors101","url":"https://github.com/ebagdasa/backdoors101"},{"title":"torchjd/torchjd","url":"https://github.com/torchjd/torchjd"},{"title":"hav4ik/Hydra","url":"https://github.com/hav4ik/Hydra"},{"title":"VICO-UoE/KD4MTL","url":"https://github.com/VICO-UoE/KD4MTL"},{"title":"salomonhotegni/mdmtn","url":"https://github.com/salomonhotegni/mdmtn"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/enhancing-gans-with-mmd-neural-architecture","title":"Enhancing GANs with MMD Neural Architecture Search, PMish Activation Function, and Adaptive Rank Decomposition","date":"2024-10-23","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/posterior-mean-rectified-flow-towards-minimum","title":"Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration","date":"2024-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":4,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/clr-gan-improving-gans-stability-and-quality","title":"CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction","date":"2024-09-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/eq-cbm-a-probabilistic-concept-bottleneck-1","title":"EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors","date":"2024-09-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/concept-graph-embedding-models-for-enhanced","title":"Concept Graph Embedding Models for Enhanced Accuracy and Interpretability","date":"2024-08-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/less-is-more-fewer-interpretable-region-via","title":"Less is More: Fewer Interpretable Region via Submodular Subset Selection","date":"2024-02-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficient-generative-adversarial-networks","title":"Efficient generative adversarial networks using linear additive-attention Transformers","date":"2024-01-17","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/improving-diffusion-based-image-synthesis-1","title":"Improving Diffusion-Based Image Synthesis with Context Prediction","date":"2024-01-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/compensation-sampling-for-improved","title":"Compensation Sampling for Improved Convergence in Diffusion Models","date":"2023-12-11","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/optimal-budgeted-rejection-sampling-for","title":"Optimal Budgeted Rejection Sampling for Generative Models","date":"2023-11-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-stackable-and-skippable-lego-bricks","title":"Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling","date":"2023-10-10","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":11,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/diffbir-towards-blind-image-restoration-with","title":"DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior","date":"2023-08-29","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/scire-solver-efficient-sampling-of-diffusion","title":"SciRE-Solver: Accelerating Diffusion Models Sampling by Score-integrand Solver with Recursive Difference","date":"2023-08-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/blackout-diffusion-generative-diffusion","title":"Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces","date":"2023-05-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":2,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/continuous-time-functional-diffusion","title":"Continuous-Time Functional Diffusion Processes","date":"2023-03-01","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/input-perturbation-reduces-exposure-bias-in","title":"Input Perturbation Reduces Exposure Bias in Diffusion Models","date":"2023-01-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/finc-flow-fast-and-invertible-k-times-k","title":"FInC Flow: Fast and Invertible $k \\times k$ Convolutions for Normalizing Flows","date":"2023-01-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/class-continuous-conditional-generative","title":"Class-Continuous Conditional Generative Neural Radiance Field","date":"2023-01-03","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/difface-blind-face-restoration-with-diffused","title":"DifFace: Blind Face Restoration with Diffused Error Contraction","date":"2022-12-13","rows_on_this_dataset":7,"code_links":2,"syntology":null},{"paper":"/paper/zero-shot-image-restoration-using-denoising","title":"Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model","date":"2022-12-01","rows_on_this_dataset":15,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":23,"samples_ran":12,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/refining-generative-process-with","title":"Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models","date":"2022-11-28","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/soft-diffusion-score-matching-for-general","title":"Soft Diffusion: Score Matching for General Corruptions","date":"2022-09-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/towards-robust-blind-face-restoration-with","title":"Towards Robust Blind Face Restoration with Codebook Lookup Transformer","date":"2022-06-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/making-sense-of-dependence-efficient-black","title":"Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure","date":"2022-06-13","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/diffusion-gan-training-gans-with-diffusion","title":"Diffusion-GAN: Training GANs with Diffusion","date":"2022-06-05","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":18,"samples_ran":13,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/maximum-likelihood-training-of-implicit","title":"Maximum Likelihood Training of Implicit Nonlinear Diffusion Models","date":"2022-05-27","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":3,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficient-vdvae-less-is-more","title":"Efficient-VDVAE: Less is more","date":"2022-03-25","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/pseudo-numerical-methods-for-diffusion-models-1","title":"Pseudo Numerical Methods for Diffusion Models on Manifolds","date":"2022-02-20","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":10,"samples_unverified":4,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/diffusevae-efficient-controllable-and-high","title":"DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents","date":"2022-01-02","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/styleswin-transformer-based-gan-for-high-1","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","date":"2021-12-20","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":5,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pure-noise-to-the-rescue-of-insufficient-data","title":"Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images","date":"2021-12-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/feature-alignment-for-approximated","title":"Feature Alignment as a Generative Process","date":"2021-06-23","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/improved-transformer-for-high-resolution-gans","title":"Improved Transformer for High-Resolution GANs","date":"2021-06-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/score-matching-model-for-unbounded-data-score-1","title":"Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation","date":"2021-06-10","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":4,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/score-based-generative-modeling-in-latent","title":"Score-based Generative Modeling in Latent Space","date":"2021-06-10","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/densely-connected-normalizing-flows","title":"Densely connected normalizing flows","date":"2021-06-08","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/consistency-regularization-for-variational","title":"Consistency Regularization for Variational Auto-Encoders","date":"2021-05-31","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/transgan-two-transformers-can-make-one-strong","title":"TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up","date":"2021-02-14","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":8,"samples_unverified":0,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/peergan-generative-adversarial-networks-with","title":"DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training","date":"2021-01-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/towards-real-world-blind-face-restoration","title":"Towards Real-World Blind Face Restoration with Generative Facial Prior","date":"2021-01-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/taming-transformers-for-high-resolution-image","title":"Taming Transformers for High-Resolution Image Synthesis","date":"2020-12-17","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":6,"samples_unverified":0,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-energy-based-models-by-diffusion-1","title":"Learning Energy-Based Models by Diffusion Recovery Likelihood","date":"2020-12-15","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/dual-contradistinctive-generative-autoencoder-1","title":"Dual Contradistinctive Generative Autoencoder","date":"2020-11-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ncp-vae-variational-autoencoders-with-noise-1","title":"A Contrastive Learning Approach for Training Variational Autoencoder Priors","date":"2020-10-06","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/progressive-semantic-aware-style","title":"Progressive Semantic-Aware Style Transformation for Blind Face Restoration","date":"2020-09-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/null-sampling-for-interpretable-and-fair","title":"Null-sampling for Interpretable and Fair Representations","date":"2020-08-12","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/nvae-a-deep-hierarchical-variational","title":"NVAE: A Deep Hierarchical Variational Autoencoder","date":"2020-07-08","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":41,"samples_ran":23,"samples_unverified":18,"pointer_only_for_licence":23,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/locally-masked-convolution-for-autoregressive","title":"Locally Masked Convolution for Autoregressive Models","date":"2020-06-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/probabilistic-auto-encoder","title":"Probabilistic Autoencoder","date":"2020-06-09","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":1,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hifacegan-face-renovation-via-collaborative","title":"HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment","date":"2020-05-11","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/adversarial-latent-autoencoders","title":"Adversarial Latent Autoencoders","date":"2020-04-09","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-u-net-based-discriminator-for-generative","title":"A U-Net Based Discriminator for Generative Adversarial Networks","date":"2020-02-28","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/augmented-normalizing-flows-bridging-the-gap","title":"Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models","date":"2020-02-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/image-processing-using-multi-code-gan-prior","title":"Image Processing Using Multi-Code GAN Prior","date":"2019-12-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/flow-contrastive-estimation-of-energy-based","title":"Flow Contrastive Estimation of Energy-Based Models","date":"2019-12-02","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/prescribed-generative-adversarial-networks","title":"Prescribed Generative Adversarial Networks","date":"2019-10-09","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/progressive-face-super-resolution-via","title":"Progressive Face Super-Resolution via Attention to Facial Landmark","date":"2019-08-22","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/deblurgan-v2-deblurring-orders-of-magnitude","title":"DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better","date":"2019-08-10","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/latent-space-factorisation-and-manipulation","title":"Latent Space Factorisation and Manipulation via Matrix Subspace Projection","date":"2019-07-26","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/residual-flows-for-invertible-generative","title":"Residual Flows for Invertible Generative Modeling","date":"2019-06-06","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":5,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/generative-latent-flow-a-framework-for-non","title":"Generative Latent Flow","date":"2019-05-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/macow-masked-convolutional-generative-flow","title":"MaCow: Masked Convolutional Generative Flow","date":"2019-02-12","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/generating-high-fidelity-images-with-subscale","title":"Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling","date":"2018-12-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-task-learning-as-multi-objective","title":"Multi-Task Learning as Multi-Objective Optimization","date":"2018-10-10","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":2,"samples_unverified":17,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/escaping-from-collapsing-modes-in-a","title":"Escaping from Collapsing Modes in a Constrained Space","date":"2018-08-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/glow-generative-flow-with-invertible-1x1","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","date":"2018-07-09","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":129,"samples_ran":75,"samples_unverified":54,"pointer_only_for_licence":44,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rise-randomized-input-sampling-for","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","date":"2018-06-19","rows_on_this_dataset":2,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":34,"samples_ran":1,"samples_unverified":33,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/high-resolution-deep-convolutional-generative","title":"High-Resolution Deep Convolutional Generative Adversarial Networks","date":"2017-11-17","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/a-unified-approach-to-interpreting-model","title":"A Unified Approach to Interpreting Model Predictions","date":"2017-05-22","rows_on_this_dataset":2,"code_links":17,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":3,"samples_unverified":5,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/axiomatic-attribution-for-deep-networks","title":"Axiomatic Attribution for Deep Networks","date":"2017-03-04","rows_on_this_dataset":2,"code_links":40,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":56,"samples_ran":36,"samples_unverified":20,"pointer_only_for_licence":17,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/grad-cam-visual-explanations-from-deep","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","date":"2016-10-07","rows_on_this_dataset":2,"code_links":126,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":141,"samples_ran":79,"samples_unverified":62,"pointer_only_for_licence":68,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/why-should-i-trust-you-explaining-the","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","date":"2016-02-16","rows_on_this_dataset":2,"code_links":27,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":5,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-inside-convolutional-networks","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","date":"2013-12-20","rows_on_this_dataset":2,"code_links":23,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":35,"samples_harvested":635,"samples_ran":328,"samples_unverified":307,"pointer_only_for_licence":202,"papers_with_no_sample_that_ran":4,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}