-
SimCLR
A Simple Framework for Contrastive Learning of Visual Representations
-
CLIP
Learning Transferable Visual Models From Natural Language Supervision
-
SayCan
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
-
R3M
R3M: A Universal Visual Representation for Robot Manipulation
-
Perceptual Loss
Perceptual Losses for Real-Time Style Transfer and Super-Resolution