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
Music Conditioned 3D Dance Generation with AIST++
Discovering Anomalous Data with Self-Supervised Learning
Improved Detection of Elusive Polyps via Machine Learning
Mapping Africa’s Buildings with Satellite Imagery
High Fidelity Image Generation Using Diffusion Models
Google at CVPR 2021
A Step Toward More Inclusive People Annotations in the Open Images Extended Dataset
Using Variational Transformer Networks to Automate Document Layout Design
Extending Contrastive Learning to the Supervised Setting
