ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders

ConvNeXt V2: 使用MAE协同设计和扩展卷积网络.

DeepViT: Towards Deeper Vision Transformer

DeepViT：构建更深的视觉Transformer.

Training data-efficient image transformers & distillation through attention

DeiT：通过注意力蒸馏训练数据高效的视觉Transformer.

Better plain ViT baselines for ImageNet-1k

在ImageNet-1k数据集上更好地训练视觉Transformer.

视觉Transformer(Vision Transformer)

Vision Transformer.

Scalable Diffusion Models with Transformers

使用Transformer实现可扩展的扩散模型.