CelebA (CelebFaces Attributes Dataset)

Introduced by Liu et al. in Deep Learning Face Attributes in the Wild

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

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Image Generation	CelebA 64x64	DDPM-IP
Image Generation	CelebA 256x256	Efficient-VDVAE
Blind Face Restoration	CelebA-Test	CodeFormer
Facial Expression Translation	CelebA	AGGAN
Image Inpainting	CelebA	DDNM
Image Generation	CelebA 128x128	U-Net GAN
Image Super-Resolution	CelebA	DDNM
Image Deblurring	CelebA	DDNM
Image Compressed Sensing	CelebA	DDNM
Image Classification	CelebA 64x64	cFlow
Image Colorization	CelebA	DDRM
HeavyMakeup/Bias-conflicting	CelebA
HairColor/Bias-conflicting	CelebA
HairColor/Unbiased	CelebA
HeavyMakeup/Unbiased	CelebA
Image Generation	CelebA	PR-BigGAN - Recall
Face Alignment	CelebA Aligned	Progressive Face SR
Face Alignment	CelebA + AFLW Unaligned	Progressive Face SR
Long-tail Learning	CelebA-5	OPeN
Multi-Task Learning	CelebA	MGDA-UB