1.4k citations · 1.8k across the 32 of their papers we have counts for
33 papers
Out-of-Dynamics Imitation Learning from Multimodal Demonstrations
Yiwen Qiu, Jialong Wu, Zhangjie Cao +1
Existing imitation learning works mainly assume that the demonstrator who collects demonstrations shares the same dynamics as the imitator. However, the assumption limits the usage…
Masked Imitation Learning: Discovering Environment-Invariant Modalities in Multimodal Demonstrations
Yilun Hao, Ruinan Wang, Zhangjie Cao +3
Multimodal demonstrations provide robots with an abundance of information to make sense of the world. However, such abundance may not always lead to good performance when it comes…
Hub-Pathway: Transfer Learning from A Hub of Pre-trained Models
Yang Shu, Zhangjie Cao, Ziyang Zhang +2
Transfer learning aims to leverage knowledge from pre-trained models to benefit the target task. Prior transfer learning work mainly transfers from a single model. However, with th…
MetaSets: Meta-Learning on Point Sets for Generalizable Representations
Chao Huang, Zhangjie Cao, Yunbo Wang +2
Deep learning techniques for point clouds have achieved strong performance on a range of 3D vision tasks. However, it is costly to annotate large-scale point sets, making it critic…
Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction
Zhangjie Cao, Erdem Bıyık, Guy Rosman +1
Multi-agent interactions are important to model for forecasting other agents' behaviors and trajectories. At a certain time, to forecast a reasonable future trajectory, each agent…
From Big to Small: Adaptive Learning to Partial-Set Domains
Zhangjie Cao, Kaichao You, Ziyang Zhang +2
Domain adaptation targets at knowledge acquisition and dissemination from a labeled source domain to an unlabeled target domain under distribution shift. Still, the common requirem…
Weakly Supervised Correspondence Learning
Zihan Wang, Zhangjie Cao, Yilun Hao +1
Correspondence learning is a fundamental problem in robotics, which aims to learn a mapping between state, action pairs of agents of different dynamics or embodiments. However, cur…
Learning from Imperfect Demonstrations via Adversarial Confidence Transfer
Zhangjie Cao, Zihan Wang, Dorsa Sadigh
Existing learning from demonstration algorithms usually assume access to expert demonstrations. However, this assumption is limiting in many real-world applications since the colle…
Learning Feasibility to Imitate Demonstrators with Different Dynamics
Zhangjie Cao, Yilun Hao, Mengxi Li +1
The goal of learning from demonstrations is to learn a policy for an agent (imitator) by mimicking the behavior in the demonstrations. Prior works on learning from demonstrations a…
Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality
Songyuan Zhang, Zhangjie Cao, Dorsa Sadigh +1
Most existing imitation learning approaches assume the demonstrations are drawn from experts who are optimal, but relaxing this assumption enables us to use a wider range of data.…
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning
Yang Shu, Zhangjie Cao, Jinghan Gao +3
Few-shot learning aims to fast adapt a deep model from a few examples. While pre-training and meta-training can create deep models powerful for few-shot generalization, we find tha…
Multi-Agent Imitation Learning with Copulas
Hongwei Wang, Lantao Yu, Zhangjie Cao +1
Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions, which is essential for und…
Zoo-Tuning: Adaptive Transfer from a Zoo of Models
Yang Shu, Zhi Kou, Zhangjie Cao +2
With the development of deep networks on various large-scale datasets, a large zoo of pretrained models are available. When transferring from a model zoo, applying classic single-m…
Open Domain Generalization with Domain-Augmented Meta-Learning
Yang Shu, Zhangjie Cao, Chenyu Wang +2
Leveraging datasets available to learn a model with high generalization ability to unseen domains is important for computer vision, especially when the unseen domain's annotated da…
Learning from Imperfect Demonstrations from Agents with Varying Dynamics
Zhangjie Cao, Dorsa Sadigh
Imitation learning enables robots to learn from demonstrations. Previous imitation learning algorithms usually assume access to optimal expert demonstrations. However, in many real…
Transfer Reinforcement Learning across Homotopy Classes
Zhangjie Cao, Minae Kwon, Dorsa Sadigh
The ability for robots to transfer their learned knowledge to new tasks -- where data is scarce -- is a fundamental challenge for successful robot learning. While fine-tuning has b…
Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving
Zhangjie Cao, Erdem Bıyık, Woodrow Z. Wang +4
Autonomous driving has achieved significant progress in recent years, but autonomous cars are still unable to tackle high-risk situations where a potential accident is likely. In s…
Robust Learning Through Cross-Task Consistency
Amir Zamir, Alexander Sax, Teresa Yeo +6
Visual perception entails solving a wide set of tasks, e.g., object detection, depth estimation, etc. The predictions made for multiple tasks from the same image are not independen…
Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction
Bingbin Liu, Ehsan Adeli, Zhangjie Cao +4
Reasoning over visual data is a desirable capability for robotics and vision-based applications. Such reasoning enables forecasting of the next events or actions in videos. In rece…
Adversarial Cross-Domain Action Recognition with Co-Attention
Boxiao Pan, Zhangjie Cao, Ehsan Adeli +1
Action recognition has been a widely studied topic with a heavy focus on supervised learning involving sufficient labeled videos. However, the problem of cross-domain action recogn…
Improving Unsupervised Domain Adaptation with Variational Information Bottleneck
Yuxuan Song, Lantao Yu, Zhangjie Cao +5
Domain adaptation aims to leverage the supervision signal of source domain to obtain an accurate model for target domain, where the labels are not available. To leverage and adapt…
Few-Shot Video Classification via Temporal Alignment
Kaidi Cao, Jingwei Ji, Zhangjie Cao +2
There is a growing interest in learning a model which could recognize novel classes with only a few labeled examples. In this paper, we propose Temporal Alignment Module (TAM), a n…
AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flows
Aditya Grover, Christopher Chute, Rui Shu +2
Given datasets from multiple domains, a key challenge is to efficiently exploit these data sources for modeling a target domain. Variants of this problem have been studied in many…
Learning to Transfer Examples for Partial Domain Adaptation
Zhangjie Cao, Kaichao You, Mingsheng Long +2
Domain adaptation is critical for learning in new and unseen environments. With domain adversarial training, deep networks can learn disentangled and transferable features that eff…