</> Code with Papers by Syntology

Datasets › CelebA

CelebA (CelebFaces Attributes Dataset)

Introduced by Ziwei Liu et al. in Deep Learning Face Attributes in the Wild1 Jan 2015 archive 2025-07-28

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.

Source: Show, Attend and Translate: Unpaired Multi-Domain Image-to-Image Translation with Visual Attention Image Source: http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 17 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Image Generation CelebA 64x64 DDPM-IP FID 1.27 Input Perturbation Reduces Exposure Bias in Diffusion Models forever208/ddpm-ip 39 Compare
Image Generation CelebA 256x256 Efficient-VDVAE bpd 0.51 Efficient-VDVAE: Less is more Rayhane-mamah/Efficient-VDVAE 17 Compare
Blind Face Restoration CelebA-Test CodeFormer LPIPS 29.9 Towards Robust Blind Face Restoration with Codebook... sczhou/codeformer 15 Compare
Image Attribution CelebA SMDL-Attribution (ICLR version) Insertion AUC score (ArcFace ResNet-101) 0.5752 Less is More: Fewer Interpretable Region via Submodular... ruoyuchen10/smdl-attribution 8 Compare
Interpretability Techniques for Deep Learning CelebA RISE Insertion AUC score 0.5703 RISE: Randomized Input Sampling for Explanation of... openvinotoolkit/datumaro +12 7 Compare
Image Generation CelebA 128x128 U-Net GAN FID 2.95 A U-Net Based Discriminator for Generative Adversarial Networks boschresearch/unetgan +2 5 Compare
Image Inpainting CelebA DDNM FID 4.54 Zero-Shot Image Restoration Using Denoising Diffusion... wyhuai/ddnm +3 5 Compare
Image Super-Resolution CelebA DDNM FID 22.27 Zero-Shot Image Restoration Using Denoising Diffusion... wyhuai/ddnm +3 5 Compare
Image Classification CelebA 64x64 cFlow Accuracy 0.82 Null-sampling for Interpretable and Fair Representations predictive-analytics-lab/nifr 3 Compare
Image Colorization CelebA DDRM Consistency 455.9 Zero-Shot Image Restoration Using Denoising Diffusion... wyhuai/ddnm +3 3 Compare
Image Deblurring CelebA DDNM FID 1.41 Zero-Shot Image Restoration Using Denoising Diffusion... wyhuai/ddnm +3 3 Compare
Concept-based Classification CelebA EQ-CBM (ResNet-34) Task Accuracy (%) 56.600 EQ-CBM: A Probabilistic Concept Bottleneck with... — 2 Compare
Face Alignment CelebA + AFLW Unaligned Progressive Face SR MOS 3.73 Progressive Face Super-Resolution via Attention to... DeokyunKim/Progressive-Face-Super-Resolution 1 Compare
Face Alignment CelebA Aligned Progressive Face SR MOS 3.73 Progressive Face Super-Resolution via Attention to... DeokyunKim/Progressive-Face-Super-Resolution 1 Compare
Image Generation CelebA FInCFlow bpd (8-bits) NaN FInC Flow: Fast and Invertible k ×k Convolutions for... — 1 Compare
Long-tail Learning CelebA-5 OPeN (WideResNet-28-10) Error Rate 19.1 Pure Noise to the Rescue of Insufficient Data: Improving... shiranzada/pure-noise 1 Compare
Multi-Task Learning CelebA MGDA-UB Error 8.25 Multi-Task Learning as Multi-Objective Optimization IntelVCL/MultiObjectiveOptimization +6 1 Compare

Papers archive 2025-07-28

30 shown of 73 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 3,477. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Enhancing GANs with MMD Neural Architecture Search, PMish Activation Function, and Adaptive Rank Decomposition 1 2 23 Oct 2024 not harvested
Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration 1 1 1 Oct 2024 ran 4 of 10 samples (6 unverified)
CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction 1 1 30 Sep 2024 not harvested
EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors 0 1 22 Sep 2024 not harvested
Concept Graph Embedding Models for Enhanced Accuracy and Interpretability 1 1 13 Aug 2024 not harvested
Less is More: Fewer Interpretable Region via Submodular Subset Selection 1 1 14 Feb 2024 ran 3 of 3 samples (0 unverified; 3 pointer-only for licence)
Efficient generative adversarial networks using linear additive-attention Transformers 2 1 17 Jan 2024 not harvested
Improving Diffusion-Based Image Synthesis with Context Prediction 0 1 4 Jan 2024 not harvested
Compensation Sampling for Improved Convergence in Diffusion Models 1 2 11 Dec 2023 not harvested
Optimal Budgeted Rejection Sampling for Generative Models 0 1 1 Nov 2023 not harvested
Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling 1 1 10 Oct 2023 ran 11 of 17 samples (6 unverified)
DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior 2 1 29 Aug 2023 not harvested
SciRE-Solver: Accelerating Diffusion Models Sampling by Score-integrand Solver with Recursive Difference 0 1 15 Aug 2023 not harvested
Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces 1 1 18 May 2023 ran 2 of 6 samples (4 unverified)
Continuous-Time Functional Diffusion Processes 1 2 1 Mar 2023 ran 0 of 3 samples (3 unverified; 3 pointer-only for licence)
Input Perturbation Reduces Exposure Bias in Diffusion Models 1 1 27 Jan 2023 ran 2 of 3 samples (1 unverified; 2 pointer-only for licence)
FInC Flow: Fast and Invertible k ×k Convolutions for Normalizing Flows 0 1 23 Jan 2023 not harvested
Class-Continuous Conditional Generative Neural Radiance Field 1 2 3 Jan 2023 not harvested
DifFace: Blind Face Restoration with Diffused Error Contraction 2 7 13 Dec 2022 not harvested
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model 4 15 1 Dec 2022 ran 12 of 23 samples (11 unverified)
Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models 2 1 28 Nov 2022 ran 2 of 2 samples (0 unverified; 2 pointer-only for licence)
Soft Diffusion: Score Matching for General Corruptions 0 1 12 Sep 2022 not harvested
Towards Robust Blind Face Restoration with Codebook Lookup Transformer 1 1 22 Jun 2022 not harvested
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure 1 2 13 Jun 2022 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Diffusion-GAN: Training GANs with Diffusion 4 1 5 Jun 2022 ran 13 of 18 samples (5 unverified)
Maximum Likelihood Training of Implicit Nonlinear Diffusion Models 1 2 27 May 2022 ran 3 of 8 samples (5 unverified)
Efficient-VDVAE: Less is more 1 2 25 Mar 2022 not harvested
Pseudo Numerical Methods for Diffusion Models on Manifolds 9 1 20 Feb 2022 ran 10 of 14 samples (4 unverified; 2 pointer-only for licence)
DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents 3 1 2 Jan 2022 not harvested
StyleSwin: Transformer-based GAN for High-resolution Image Generation 1 1 20 Dec 2021 ran 5 of 5 samples (0 unverified; 3 pointer-only for licence)

The full list of 73 is in the JSON twin.

Dataset loaders archive 2025-07-28

pytorch.org/vision/stable/generated/torchvision.datasets.CelebA.htmlpytorch/visionpytorch
docs.activeloop.ai/datasets/celeba-datasetactiveloopai/Hubtfpytorch
www.tensorflow.org/datasets/catalog/celeb_atensorflow/datasetstfjax

3 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Image ClassificationImage GenerationImage Super-ResolutionFace AlignmentLong-tail LearningImage InpaintingMulti-Task LearningImage DeblurringImage Compressed SensingConcept-based ClassificationBlind Face RestorationFacial Expression TranslationImage ColorizationImage AttributionInterpretability Techniques for Deep LearningPhysical Attribute PredictionHairColor/UnbiasedHairColor/Bias-conflictingHeavyMakeup/UnbiasedHeavyMakeup/Bias-conflicting

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

Chinese

Variants archive 2025-07-28

  • 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

12 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections