Trevor Darrell

is this you? claim profile

∙ 1 follower
berkeley college

Professor at University of California, Berkeley

DETReg: Unsupervised Pretraining with Region Priors for Object Detection

Unsupervised pretraining has recently proven beneficial for computer vis...
06/08/2021 ∙ by Amir Bar, et al. ∙ 6 ∙ share

read it
Towards Learning to Play Piano with Dexterous Hands and Touch

The virtuoso plays the piano with passion, poetry and extraordinary tech...
06/03/2021 ∙ by Huazhe Xu, et al. ∙ 0 ∙ share

read it
PyTouch: A Machine Learning Library for Touch Processing

With the increased availability of rich tactile sensors, there is an equ...
05/26/2021 ∙ by Mike Lambeta, et al. ∙ 0 ∙ share

read it
Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks

Adversarial attacks optimize against models to defeat defenses. Existing...
05/18/2021 ∙ by Dequan Wang, et al. ∙ 20 ∙ share

read it
Auto-Tuned Sim-to-Real Transfer

Policies trained in simulation often fail when transferred to the real w...
04/15/2021 ∙ by Yuqing Du, et al. ∙ 0 ∙ share

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

The threat of online misinformation is hard to overestimate, with advers...
04/13/2021 ∙ by Grace Luo, et al. ∙ 0 ∙ share

read it
Strumming to the Beat: Audio-Conditioned Contrastive Video Textures

We introduce a non-parametric approach for infinite video texture synthe...
04/06/2021 ∙ by Medhini Narasimhan, et al. ∙ 3 ∙ share

read it
Confidence Adaptive Anytime Pixel-Level Recognition

Anytime inference requires a model to make a progression of predictions ...
04/01/2021 ∙ by Zhuang Liu, et al. ∙ 0 ∙ share

read it
Self-Supervised Pretraining Improves Self-Supervised Pretraining

While self-supervised pretraining has proven beneficial for many compute...
03/23/2021 ∙ by Colorado J. Reed, et al. ∙ 45 ∙ share

read it
Instance-Aware Predictive Navigation in Multi-Agent Environments

In this work, we aim to achieve efficient end-to-end learning of driving...
01/14/2021 ∙ by Jinkun Cao, et al. ∙ 5 ∙ share

read it
Minimax Active Learning

Active learning aims to develop label-efficient algorithms by querying t...
12/18/2020 ∙ by Sayna Ebrahimi, et al. ∙ 0 ∙ share

read it
Temporal Action Detection with Multi-level Supervision

Training temporal action detection in videos requires large amounts of l...
11/24/2020 ∙ by Baifeng Shi, et al. ∙ 0 ∙ share

read it
Modularity Improves Out-of-Domain Instruction Following

We propose a modular architecture for following natural language instruc...
10/24/2020 ∙ by Rodolfo Corona, et al. ∙ 3 ∙ share

read it
Auxiliary Task Reweighting for Minimum-data Learning

Supervised learning requires a large amount of training data, limiting i...
10/16/2020 ∙ by Baifeng Shi, et al. ∙ 0 ∙ share

read it
Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation

The success of supervised learning hinges on the assumption that the tra...
10/09/2020 ∙ by Bo Li, et al. ∙ 5 ∙ share

read it
Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting

The goal of continual learning (CL) is to learn a sequence of tasks with...
10/04/2020 ∙ by Sayna Ebrahimi, et al. ∙ 9 ∙ share

read it
Evaluating Self-Supervised Pretraining Without Using Labels

A common practice in unsupervised representation learning is to use labe...
09/16/2020 ∙ by Colorado Reed, et al. ∙ 8 ∙ share

read it
Identity-Aware Multi-Sentence Video Description

Standard video and movie description tasks abstract away from person ide...
08/22/2020 ∙ by Jae Sung Park, et al. ∙ 11 ∙ share

read it
What Should Not Be Contrastive in Contrastive Learning

Recent self-supervised contrastive methods have been able to produce imp...
08/13/2020 ∙ by Tete Xiao, et al. ∙ 15 ∙ share

read it
Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body Dynamics

We propose a novel learned deep prior of body motion for 3D hand shape s...
07/23/2020 ∙ by Evonne Ng, et al. ∙ 10 ∙ share

read it
Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation

We introduce a learning-based approach for room navigation using semanti...
07/20/2020 ∙ by Medhini Narasimhan, et al. ∙ 2 ∙ share

read it
Video Prediction via Example Guidance

In video prediction tasks, one major challenge is to capture the multi-m...
07/03/2020 ∙ by Jingwei Xu, et al. ∙ 6 ∙ share

read it
Compositional Video Synthesis with Action Graphs

Videos of actions are complex spatio-temporal signals, containing rich c...
06/27/2020 ∙ by Amir Bar, et al. ∙ 3 ∙ share

read it
Fully Test-time Adaptation by Entropy Minimization

Faced with new and different data during testing, a model must adapt its...
06/18/2020 ∙ by Dequan Wang, et al. ∙ 18 ∙ share

read it
Quasi-Dense Instance Similarity Learning

Similarity metrics for instances have drawn much attention, due to their...
06/11/2020 ∙ by Jiangmiao Pang, et al. ∙ 1 ∙ share

read it
Reducing Class Collapse in Metric Learning with Easy Positive Sampling

Metric learning seeks perceptual embeddings where visually similar insta...
06/09/2020 ∙ by Elad Levi, et al. ∙ 0 ∙ share

read it
ParkPredict: Motion and Intent Prediction of Vehicles in Parking Lots

We investigate the problem of predicting driver behavior in parking lots...
04/21/2020 ∙ by Xu Shen, et al. ∙ 9 ∙ share

read it
Contrastive Examples for Addressing the Tyranny of the Majority

Computer vision algorithms, e.g. for face recognition, favour groups of ...
04/14/2020 ∙ by Viktoriia Sharmanska, et al. ∙ 6 ∙ share

read it
Spatio-Temporal Action Detection with Multi-Object Interaction

Spatio-temporal action detection in videos requires localizing the actio...
04/01/2020 ∙ by Huijuan Xu, et al. ∙ 13 ∙ share

read it
Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning

Weakly-supervised action localization problem requires training a model ...
03/31/2020 ∙ by Zhekun Luo, et al. ∙ 5 ∙ share

read it
Revisiting Few-shot Activity Detection with Class Similarity Control

Many interesting events in the real world are rare making preannotated m...
03/31/2020 ∙ by Huijuan Xu, et al. ∙ 28 ∙ share

read it
Adversarial Continual Learning

Continual learning aims to learn new tasks without forgetting previously...
03/21/2020 ∙ by Sayna Ebrahimi, et al. ∙ 8 ∙ share

read it
Frustratingly Simple Few-Shot Object Detection

Detecting rare objects from a few examples is an emerging problem. Prior...
03/16/2020 ∙ by Xin Wang, et al. ∙ 10 ∙ share

read it
Rethinking Image Mixture for Unsupervised Visual Representation Learning

In supervised learning, smoothing label/prediction distribution in neura...
03/11/2020 ∙ by Zhiqiang Shen, et al. ∙ 8 ∙ share

read it
A New Meta-Baseline for Few-Shot Learning

Meta-learning has become a popular framework for few-shot learning in re...
03/09/2020 ∙ by Yinbo Chen, et al. ∙ 11 ∙ share

read it
Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning

Learning robotic manipulation tasks using reinforcement learning with sp...
12/23/2019 ∙ by Richard Li, et al. ∙ 23 ∙ share

read it
Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks

Human action is naturally compositional: humans can easily recognize and...
12/20/2019 ∙ by Joanna Materzyńska, et al. ∙ 12 ∙ share

read it
Learning Canonical Representations for Scene Graph to Image Generation

Generating realistic images of complex visual scenes becomes very challe...
12/16/2019 ∙ by Roei Herzig, et al. ∙ 15 ∙ share

read it
Semantic Bottleneck Scene Generation

Coupling the high-fidelity generation capabilities of label-conditional ...
11/26/2019 ∙ by Samaneh Azadi, et al. ∙ 33 ∙ share

read it
Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for TextVQA

Many visual scenes contain text that carries crucial information, and it...
11/14/2019 ∙ by Ronghang Hu, et al. ∙ 22 ∙ share

read it
Plan Arithmetic: Compositional Plan Vectors for Multi-Task Control

Autonomous agents situated in real-world environments must be able to ma...
10/30/2019 ∙ by Coline Devin, et al. ∙ 12 ∙ share

read it
Regularization Matters in Policy Optimization

Deep Reinforcement Learning (Deep RL) has been receiving increasingly mo...
10/21/2019 ∙ by Zhuang Liu, et al. ∙ 21 ∙ share

read it
Transferable Recognition-Aware Image Processing

Recent progress in image recognition has stimulated the deployment of vi...
10/21/2019 ∙ by Zhuang Liu, et al. ∙ 0 ∙ share

read it
Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization

Humans can learn task-agnostic priors from interactive experience and ut...
10/17/2019 ∙ by Huazhe Xu, et al. ∙ 8 ∙ share

read it
Unsupervised Domain Adaptation through Self-Supervision

This paper addresses unsupervised domain adaptation, the setting where l...
09/26/2019 ∙ by Yu Sun, et al. ∙ 18 ∙ share

read it
Dynamic Scale Inference by Entropy Minimization

Given the variety of the visual world there is not one true scale for re...
08/08/2019 ∙ by Dequan Wang, et al. ∙ 0 ∙ share

read it
Task-Aware Deep Sampling for Feature Generation

The human ability to imagine the variety of appearances of novel objects...
06/11/2019 ∙ by Xin Wang, et al. ∙ 0 ∙ share

read it
Uncertainty-guided Continual Learning with Bayesian Neural Networks

Continual learning aims to learn new tasks without forgetting previously...
06/06/2019 ∙ by Sayna Ebrahimi, et al. ∙ 0 ∙ share

read it
Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) requires grounding instructions, su...
06/02/2019 ∙ by Ronghang Hu, et al. ∙ 0 ∙ share

read it
Monocular Plan View Networks for Autonomous Driving

Convolutions on monocular dash cam videos capture spatial invariances in...
05/16/2019 ∙ by Dequan Wang, et al. ∙ 0 ∙ share

read it

Trevor Darrell

Featured Co-authors