Scaling Vision with Sparse Mixture of Experts
Improving Vision Transformer Efficiency and Accuracy by Learning to Tokenize
Making Better Future Predictions by Watching Unlabeled Videos
Model Ensembles Are Faster Than You Think
Deciding Which Tasks Should Train Together in Multi-Task Neural Networks
SimVLM: Simple Visual Language Model Pre-training with Weak Supervision
Self-Supervised Learning Advances Medical Image Classification
Google at ICCV 2021
Pathdreamer: A World Model for Indoor Navigation
Toward Fast and Accurate Neural Networks for Image Recognition
Revisiting Mask-Head Architectures for Novel Class Instance Segmentation
