activity
20172022
most citedEarly Convolutions Help Transformers See Better

353 citations · 425 across the 4 of their papers we have counts for

collaborators

13 papers

cs.RO202227 cited

Real-World Robot Learning with Masked Visual Pre-training

Ilija Radosavovic, Tete Xiao, Stephen James +3

In this work, we explore self-supervised visual pre-training on images from diverse, in-the-wild videos for real-world robotic tasks. Like prior work, our visual representations ar…

cs.CV202241 cited

Masked Visual Pre-training for Motor Control

Tete Xiao, Ilija Radosavovic, Trevor Darrell +1

This paper shows that self-supervised visual pre-training from real-world images is effective for learning motor control tasks from pixels. We first train the visual representation…

cs.CV2021353 cited

Early Convolutions Help Transformers See Better

Tete Xiao, Mannat Singh, Eric Mintun +3

Vision transformer (ViT) models exhibit substandard optimizability. In particular, they are sensitive to the choice of optimizer (AdamW vs. SGD), optimizer hyperparameters, and tra…

cs.CV2021

Region Similarity Representation Learning

Tete Xiao, Colorado J Reed, Xiaolong Wang +2

We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and se…

cs.RO20204 cited

Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency

Qiang Zhang, Tete Xiao, Alexei A. Efros +2

At the heart of many robotics problems is the challenge of learning correspondences across domains. For instance, imitation learning requires obtaining correspondence between human…

cs.CV2020

What Should Not Be Contrastive in Contrastive Learning

Tete Xiao, Xiaolong Wang, Alexei A. Efros +1

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. How…