1 code implementation • 30 Nov 2016 • Debidatta Dwibedi, Tomasz Malisiewicz, Vijay Badrinarayanan, Andrew Rabinovich
We present a Deep Cuboid Detector which takes a consumer-quality RGB image of a cluttered scene and localizes all 3D cuboids (box-like objects).
6 code implementations • ICCV 2017 • Debidatta Dwibedi, Ishan Misra, Martial Hebert
In this paper, we propose a simple approach to generate large annotated instance datasets with minimal effort.
no code implementations • 2 Aug 2018 • Debidatta Dwibedi, Jonathan Tompson, Corey Lynch, Pierre Sermanet
In this work we explore a new approach for robots to teach themselves about the world simply by observing it.
3 code implementations • ICLR 2019 • Ilya Kostrikov, Kumar Krishna Agrawal, Debidatta Dwibedi, Sergey Levine, Jonathan Tompson
We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework.
2 code implementations • CVPR 2019 • Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, Andrew Zisserman
We introduce a self-supervised representation learning method based on the task of temporal alignment between videos.
Ranked #1 on Video Alignment on UPenn Action
no code implementations • 25 Sep 2019 • Ross Goroshin, Jonathan Tompson, Debidatta Dwibedi
Fully convolutional deep correlation networks are integral components of state-of- the-art approaches to single object visual tracking.
no code implementations • 8 Jan 2020 • Ross Goroshin, Jonathan Tompson, Debidatta Dwibedi
Despite these strong priors, we show that deep trackers often default to tracking by saliency detection - without relying on the object instance representation.
no code implementations • CVPR 2020 • Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, Andrew Zisserman
We present an approach for estimating the period with which an action is repeated in a video.
4 code implementations • ICCV 2021 • Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, Andrew Zisserman
On semi-supervised learning benchmarks we improve performance significantly when only 1% ImageNet labels are available, from 53. 8% to 56. 5%.
Ranked #1 on Image Classification on PASCAL VOC 2007
1 code implementation • 7 Jun 2021 • Kevin Zakka, Andy Zeng, Pete Florence, Jonathan Tompson, Jeannette Bohg, Debidatta Dwibedi
We investigate the visual cross-embodiment imitation setting, in which agents learn policies from videos of other agents (such as humans) demonstrating the same task, but with stark differences in their embodiments -- shape, actions, end-effector dynamics, etc.
no code implementations • 12 May 2022 • Negin Heravi, Ayzaan Wahid, Corey Lynch, Pete Florence, Travis Armstrong, Jonathan Tompson, Pierre Sermanet, Jeannette Bohg, Debidatta Dwibedi
Our self-supervised representations are learned by observing the agent freely interacting with different parts of the environment and is queried in two different settings: (i) policy learning and (ii) object location prediction.
1 code implementation • 10 Feb 2023 • Thomas Mulc, Debidatta Dwibedi
In semi-supervised learning, student-teacher distribution matching has been successful in improving performance of models using unlabeled data in conjunction with few labeled samples.
no code implementations • 23 Jan 2024 • Michael Ahn, Debidatta Dwibedi, Chelsea Finn, Montse Gonzalez Arenas, Keerthana Gopalakrishnan, Karol Hausman, Brian Ichter, Alex Irpan, Nikhil Joshi, Ryan Julian, Sean Kirmani, Edward Lee, Sergey Levine, Yao Lu, Isabel Leal, Sharath Maddineni, Kanishka Rao, Dorsa Sadigh, Pannag Sanketi, Pierre Sermanet, Quan Vuong, Stefan Welker, Fei Xia, Ted Xiao, Peng Xu, Steve Xu, Zhuo Xu
We experimentally show that such "in-the-wild" data collected by AutoRT is significantly more diverse, and that AutoRT's use of LLMs allows for instruction following data collection robots that can align to human preferences.
no code implementations • 4 Mar 2024 • Suneel Belkhale, Tianli Ding, Ted Xiao, Pierre Sermanet, Quon Vuong, Jonathan Tompson, Yevgen Chebotar, Debidatta Dwibedi, Dorsa Sadigh
Predicting these language motions as an intermediate step between tasks and actions forces the policy to learn the shared structure of low-level motions across seemingly disparate tasks.
no code implementations • 18 Mar 2024 • Debidatta Dwibedi, Vidhi Jain, Jonathan Tompson, Andrew Zisserman, Yusuf Aytar
The model, FlexCap, is trained to produce length-conditioned captions for input bounding boxes, and this allows control over the information density of its output, with descriptions ranging from concise object labels to detailed captions.
no code implementations • 19 Mar 2024 • Vidhi Jain, Maria Attarian, Nikhil J Joshi, Ayzaan Wahid, Danny Driess, Quan Vuong, Pannag R Sanketi, Pierre Sermanet, Stefan Welker, Christine Chan, Igor Gilitschenski, Yonatan Bisk, Debidatta Dwibedi
Given a video demonstration of a manipulation task and current visual observations, Vid2Robot directly produces robot actions.