Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Trevor Darrell

Early Convolutions Help Transformers See Better


Jul 12, 2021
Tete Xiao, Mannat Singh, Eric Mintun, Trevor Darrell, Piotr Dollár, Ross Girshick


  Access Paper or Ask Questions

Predicting with Confidence on Unseen Distributions


Jul 07, 2021
Devin Guillory, Vaishaal Shankar, Sayna Ebrahimi, Trevor Darrell, Ludwig Schmidt


  Access Paper or Ask Questions

CLIP-It! Language-Guided Video Summarization


Jul 01, 2021
Medhini Narasimhan, Anna Rohrbach, Trevor Darrell

* Website at https://medhini.github.io/clip_it/ 

  Access Paper or Ask Questions

Towards Learning to Play Piano with Dexterous Hands and Touch


Jun 08, 2021
Huazhe Xu, Yuping Luo, Shaoxiong Wang, Trevor Darrell, Roberto Calandra


  Access Paper or Ask Questions

DETReg: Unsupervised Pretraining with Region Priors for Object Detection


Jun 08, 2021
Amir Bar, Xin Wang, Vadim Kantorov, Colorado J Reed, Roei Herzig, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson

* preprint, under review 

  Access Paper or Ask Questions

PyTouch: A Machine Learning Library for Touch Processing


May 26, 2021
Mike Lambeta, Huazhe Xu, Jingwei Xu, Po-Wei Chou, Shaoxiong Wang, Trevor Darrell, Roberto Calandra

* 7 pages. Accepted at ICRA 2021 

  Access Paper or Ask Questions

Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks


May 18, 2021
Dequan Wang, An Ju, Evan Shelhamer, David Wagner, Trevor Darrell


  Access Paper or Ask Questions

Robust Object Detection via Instance-Level Temporal Cycle Confusion


Apr 16, 2021
Xin Wang, Thomas E. Huang, Benlin Liu, Fisher Yu, Xiaolong Wang, Joseph E. Gonzalez, Trevor Darrell


  Access Paper or Ask Questions

Auto-Tuned Sim-to-Real Transfer


Apr 15, 2021
Yuqing Du, Olivia Watkins, Trevor Darrell, Pieter Abbeel, Deepak Pathak

* ICRA 2021. First two authors contributed equally. Website at https://yuqingd.github.io/autotuned-sim2real/ 

  Access Paper or Ask Questions

NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media


Apr 13, 2021
Grace Luo, Trevor Darrell, Anna Rohrbach

* 8 pages, 4 figures 

  Access Paper or Ask Questions

Strumming to the Beat: Audio-Conditioned Contrastive Video Textures


Apr 06, 2021
Medhini Narasimhan, Shiry Ginosar, Andrew Owens, Alexei A. Efros, Trevor Darrell

* Project website at https://medhini.github.io/audio_video_textures/ 

  Access Paper or Ask Questions

Confidence Adaptive Anytime Pixel-Level Recognition


Apr 01, 2021
Zhuang Liu, Trevor Darrell, Evan Shelhamer

* 16 pages, 12 figures 

  Access Paper or Ask Questions

Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation


Mar 31, 2021
Xiangyu Yue, Zangwei Zheng, Shanghang Zhang, Yang Gao, Trevor Darrell, Kurt Keutzer, Alberto Sangiovanni Vincentelli

* CVPR 2021 

  Access Paper or Ask Questions

Self-Supervised Pretraining Improves Self-Supervised Pretraining


Mar 25, 2021
Colorado J. Reed, Xiangyu Yue, Ani Nrusimha, Sayna Ebrahimi, Vivek Vijaykumar, Richard Mao, Bo Li, Shanghang Zhang, Devin Guillory, Sean Metzger, Kurt Keutzer, Trevor Darrell


  Access Paper or Ask Questions

Region Similarity Representation Learning


Mar 24, 2021
Tete Xiao, Colorado J Reed, Xiaolong Wang, Kurt Keutzer, Trevor Darrell


  Access Paper or Ask Questions

Monocular Quasi-Dense 3D Object Tracking


Mar 12, 2021
Hou-Ning Hu, Yung-Hsu Yang, Tobias Fischer, Trevor Darrell, Fisher Yu, Min Sun

* 24 pages, 14 figures, including appendix (6 pages) 

  Access Paper or Ask Questions

Instance-Aware Predictive Navigation in Multi-Agent Environments


Jan 14, 2021
Jinkun Cao, Xin Wang, Trevor Darrell, Fisher Yu


  Access Paper or Ask Questions

Minimax Active Learning


Dec 18, 2020
Sayna Ebrahimi, William Gan, Kamyar Salahi, Trevor Darrell

* Project page is available at https://people.eecs.berkeley.edu/~sayna/mal.html 

  Access Paper or Ask Questions

Temporal Action Detection with Multi-level Supervision


Nov 24, 2020
Baifeng Shi, Qi Dai, Judy Hoffman, Kate Saenko, Trevor Darrell, Huijuan Xu


  Access Paper or Ask Questions

Fighting Copycat Agents in Behavioral Cloning from Observation Histories


Oct 28, 2020
Chuan Wen, Jierui Lin, Trevor Darrell, Dinesh Jayaraman, Yang Gao

* Published at NeurIPS 2020 9 pages(exclude reference and appendices) 

  Access Paper or Ask Questions

Modularity Improves Out-of-Domain Instruction Following


Oct 24, 2020
Rodolfo Corona, Daniel Fried, Coline Devin, Dan Klein, Trevor Darrell


  Access Paper or Ask Questions

Auxiliary Task Reweighting for Minimum-data Learning


Oct 16, 2020
Baifeng Shi, Judy Hoffman, Kate Saenko, Trevor Darrell, Huijuan Xu

* NeurIPS 2020. Project page: https://sites.google.com/view/auxiliary-task-reweighting/home 

  Access Paper or Ask Questions

Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation


Oct 12, 2020
Bo Li, Yezhen Wang, Shanghang Zhang, Dongsheng Li, Trevor Darrell, Kurt Keutzer, Han Zhao

* Preprint 

  Access Paper or Ask Questions

Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting


Oct 04, 2020
Sayna Ebrahimi, Suzanne Petryk, Akash Gokul, William Gan, Joseph E. Gonzalez, Marcus Rohrbach, Trevor Darrell


  Access Paper or Ask Questions

Evaluating Self-Supervised Pretraining Without Using Labels


Sep 16, 2020
Colorado Reed, Sean Metzger, Aravind Srinivas, Trevor Darrell, Kurt Keutzer


  Access Paper or Ask Questions

ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation


Sep 07, 2020
Sicheng Zhao, Yezhen Wang, Bo Li, Bichen Wu, Yang Gao, Pengfei Xu, Trevor Darrell, Kurt Keutzer


  Access Paper or Ask Questions

Hierarchical Style-based Networks for Motion Synthesis


Aug 24, 2020
Jingwei Xu, Huazhe Xu, Bingbing Ni, Xiaokang Yang, Xiaolong Wang, Trevor Darrell

* ECCV 2020, Project Page:\ 

  Access Paper or Ask Questions

Identity-Aware Multi-Sentence Video Description


Aug 22, 2020
Jae Sung Park, Trevor Darrell, Anna Rohrbach

* Project link at https://sites.google.com/site/describingmovies/lsmdc-2019/ 

  Access Paper or Ask Questions