Notes
🔍
38 links
Type
Site
Vision Transformers › Core ViT 5 terms
Class Token Pooling 2 links
CLS Token 2 links
Image Patches 2 links
Patch Embedding 2 links
Vision Transformer (ViT) 2 links
Vision Transformers › ViT Variants 5 terms
BEiT 2 links
DeiT (Data-efficient Image Transformer) 2 links
Hybrid CNN-Transformer 2 links
Shifted Windows 2 links
Swin Transformer 2 links
Vision Transformers › Self-Supervised Visual Learning 9 terms
ALIGN 2 links
BYOL 2 links
CLIP 2 links
DINO (Self-Supervised) 2 links
DINOv2 2 links
Masked Autoencoder (MAE) 2 links
MoCo 2 links
OpenCLIP 2 links
SimCLR 2 links
No terms or links match your search.