📄️ [20.10] ViT
Pioneering a New World
📄️ [20.12] DeiT
Distillation ViT
📄️ [21.02] CPVT
Conditional Positional Encodings
📄️ [21.02] PVT
Spatial Reduction Attention Mechanism
📄️ [21.03] Swin Transformer
The Dance Begins
📄️ [21.05] MLP-Mixer
Less Loss is Gain
📄️ [21.06] BEiT
Discrete Encoding Pre-Training
📄️ [21.11] MAE
A Quarter of the Clue
📄️ [21.11] PoolFormer
You Need a Meta!
📄️ [22.01] ConvMixer
Convolutional Mixer
📄️ [22.08] BEiT v2
Hidden Codes in High Dimensions
📄️ [22.10] CAFormer
MetaFormer User Manual