WYXOGO
Diffusion Models
So far, there are many models to generate images, such as GAN, VAE, etc. But each has its own drawbacks. For example, GAN is difficult to train and less deversity in genration, and VAE is difficult to generate high-quality images.
Animatomy: an Animator-centric, Anatomically Inspired System for 3D Facial Modeling, Animation and Transfer
Animatomy: an Animator-centric, Anatomically Inspired System for 3D Facial Modeling, Animation and Transfe
机器学习算法总结
机器学习算法思想总结
关于MLP的一些观点和一些未来可能的方向 【Can Attention Enable MLPs To Catch Up With CNNs】
关于MLP的一些观点和一些未来可能的方向【Can Attention Enable MLPs To Catch Up With CNNs】
Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
Swin Transformer论文解读与源码分析
Swin Transformer论文解读与源码分析
Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation
RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition
RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition
【多层感知机混合器】MLP-Mixer: An all-MLP Architecture for Visio
MLP-Mixer: An all-MLP Architecture for Visio
目标检测新范式：End-to-End Object Detection with Transformers
End-to-End Object Detection with Transformers