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
Proceedings ArticleDOI
Learning modular neural network policies for multi-task and multi-robot transfer
TL;DR: The authors decompose neural network policies into task-specific and robot-specific modules, where the task specific modules are shared across robots and the robot specific modules were shared across all tasks on that robot, and exploit this decomposition to train mix-and-match modules that can solve new robot-task combinations.
Patent
Pyramid match kernel and related techniques
Kristen Grauman,Trevor Darrell +1 more
TL;DR: In this article, a method for classifying or comparing objects includes detecting points of interest within two objects, computing feature descriptors at said points of interests, forming a multi-resolution histogram over feature descriptor for each object and computing a weighted intersection of multi-resolved histogram of each object.
Proceedings Article
Speaker-Follower Models for Vision-and-Language Navigation
Daniel Fried,Ronghang Hu,Volkan Cirik,Anna Rohrbach,Jacob Andreas,Louis-Philippe Morency,Taylor Berg-Kirkpatrick,Kate Saenko,Dan Klein,Trevor Darrell +9 more
TL;DR: Experiments show that all three components of this approach---speaker-driven data augmentation, pragmatic reasoning and panoramic action space---dramatically improve the performance of a baseline instruction follower, more than doubling the success rate over the best existing approach on a standard benchmark.
Book ChapterDOI
Discovering Latent Domains for Multisource Domain Adaptation
TL;DR: This paper presents both a novel domain transform mixture model which outperforms a single transform model when multiple domains are present, and a novel constrained clustering method that successfully discovers latent domains.
Posted Content
Frustratingly Simple Few-Shot Object Detection.
TL;DR: This work finds that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task, and establishes a new state of the art on the revised benchmarks.