T
Trevor Darrell
Researcher at University of California, Berkeley
Publications - 734
Citations - 222973
Trevor Darrell is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 148, co-authored 678 publications receiving 181113 citations. Previous affiliations of Trevor Darrell include Massachusetts Institute of Technology & Boston University.
Papers
More filters
Journal ArticleDOI
Refine and Represent: Region-to-Object Representation Learning
Akash Gokul,Konstantinos Kallidromitis,Shu-fang Li,Yusuke Kato,Kazuki Kozuka,Trevor Darrell,Colorado Reed +6 more
TL;DR: After pretraining on ImageNet, R2O pretrained models are able to surpass existing state-of-the-art in unsupervised object segmentation on the Caltech-UCSD Birds 200-2011 dataset without any further training.
Posted Content
Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks.
TL;DR: Dent as discussed by the authors improves the robustness of adversarially trained defenses and nominally trained models against white-box, black-box and adaptive attacks on CIFAR-10/100 and ImageNet.
Hierarchical Deep Reinforcement Learning Agent with Counter Self-play on Competitive Games
TL;DR: Hierarchical Agent with Self-Play is developed, a learning approach for obtaining hierarchically structured policies that can achieve higher performance than conventional self-play on competitive games through the use of a diverse pool of sub-policies from Counter Self- play (CSP).
Book ChapterDOI
Geometric and Statistical Approaches to Audiovisual Segmentation
TL;DR: Multimodal approaches are proposed for segmenting multiple speakers using geometric or statistical techniques and an initial integration effort is discussed.
Proceedings Article
Location Estimation with a Differential Update Network
Ali Rahimi,Trevor Darrell +1 more
TL;DR: An online algorithm is derived which approximately updates the posterior as pairwise measurements between the hidden variables become available and can be thought of as a Kalman Filter which simplifies the state covariance matrix after incorporating each measurement.