CelebA
A large-scale celebrity face attribute dataset containing approximately 200,000 celebrity face images, each annotated with 40 binary attributes such as smiling, wearing glasses, and having a beard. It is widely used for face attribute recognition and generative model evaluation.
Timeline (last 90 days)
The authors validate the effectiveness of the diagnostic metrics in a fully observed simulation environment and apply the method to six pretrained vision Transformer models, testing on the SVG-World benchmark and evaluating two of them on CelebA.
The 128×128 CelebA version in this article adjusts the stride to make the latent feature map 8×8×256 and adds BatchNorm and LeakyReLU after each convolution, where BatchNorm is an additional addition not described in the original paper.
The research team validated HnS on two datasets, CelebA and COCO-Stuff.
CelebA is a large-scale dataset containing approximately 200,000 celebrity face images, each annotated with 40 binary attribute labels.
All Facts (4)
The 128×128 CelebA version in this article adjusts the stride to make the latent feature map 8×8×256 and adds BatchNorm and LeakyReLU after each convolution, where BatchNorm is an additional addition not described in the original paper.
50%UnverifiedThe research team validated HnS on two datasets, CelebA and COCO-Stuff.
50%UnverifiedCelebA is a large-scale dataset containing approximately 200,000 celebrity face images, each annotated with 40 binary attribute labels.
50%UnverifiedThe authors validate the effectiveness of the diagnostic metrics in a fully observed simulation environment and apply the method to six pretrained vision Transformer models, testing on the SVG-World benchmark and evaluating two of them on CelebA.
50%