no code implementations • 3 Feb 2023 • Chao Yu, Jiaxuan Gao, Weilin Liu, Botian Xu, Hao Tang, Jiaqi Yang, Yu Wang, Yi Wu
A crucial limitation of this framework is that every policy in the pool is optimized w. r. t.
no code implementations • 9 Jan 2023 • Chao Yu, Xinyi Yang, Jiaxuan Gao, Jiayu Chen, Yunfei Li, Jijia Liu, Yunfei Xiang, Ruixin Huang, Huazhong Yang, Yi Wu, Yu Wang
Simply waiting for every robot being ready for the next action can be particularly time-inefficient.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
no code implementations • 17 Dec 2022 • Zhecheng Yuan, Zhengrong Xue, Bo Yuan, Xueqian Wang, Yi Wu, Yang Gao, Huazhe Xu
Hence, we propose Pre-trained Image Encoder for Generalizable visual reinforcement learning (PIE-G), a simple yet effective framework that can generalize to the unseen visual scenarios in a zero-shot manner.
no code implementations • 17 Nov 2022 • Kevin Du, Ian Gemp, Yi Wu, Yingying Wu
Reinforcement learning has recently been used to approach well-known NP-hard combinatorial problems in graph theory.
no code implementations • 11 Nov 2022 • Lianshang Cai, Linhao Zhang, Dehong Ma, Jun Fan, Daiting Shi, Yi Wu, Zhicong Cheng, Simiu Gu, Dawei Yin
In this paper, we focus on two key questions in knowledge distillation for ranking models: 1) how to ensemble knowledge from multi-teacher; 2) how to utilize the label information of data in the distillation process.
no code implementations • 10 Oct 2022 • Pei Li, Zhijun Liu, Luyi Chang, Jialiang Peng, Yi Wu
This is because most drones still use centralized cloud-based data processing, which may lead to leakage of data collected by drones.
no code implementations • 20 Jul 2022 • Xiangyu Miao, Jiahe Wang, Yanan Chang, Yi Wu, Shangfei Wang
Learning from synthetic images plays an important role in facial expression recognition task due to the difficulties of labeling the real images, and it is challenging because of the gap between the synthetic images and real images.
no code implementations • 20 Jul 2022 • Yanan Chang, Yi Wu, Xiangyu Miao, Jiahe Wang, Shangfei Wang
The 4th competition on affective behavior analysis in the wild (ABAW) provided images with valence/arousal, expression and action unit labels.
no code implementations • 24 Jun 2022 • Yunfei Li, Tian Gao, Jiaqi Yang, Huazhe Xu, Yi Wu
It has been a recent trend to leverage the power of supervised learning (SL) towards more effective reinforcement learning (RL) methods.
no code implementations • 15 Jun 2022 • Wei Fu, Chao Yu, Zelai Xu, Jiaqi Yang, Yi Wu
Despite all the advantages, we revisit these two principles and show that in certain scenarios, e. g., environments with a highly multi-modal reward landscape, value decomposition, and parameter sharing can be problematic and lead to undesired outcomes.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
no code implementations • 28 May 2022 • Kan Xie, Zhe Zhang, Bo Li, Jiawen Kang, Dusit Niyato, Shengli Xie, Yi Wu
However, for machine learning-based traffic sign recognition on the Internet of Vehicles (IoV), a large amount of traffic sign data from distributed vehicles is needed to be gathered in a centralized server for model training, which brings serious privacy leakage risk because of traffic sign data containing lots of location privacy information.
1 code implementation • 19 Apr 2022 • Wenbin Zou, Tian Ye, Weixin Zheng, Yunchen Zhang, Liang Chen, Yi Wu
Recently, deep learning has been successfully applied to the single-image super-resolution (SISR) with remarkable performance.
1 code implementation • 12 Apr 2022 • Yunfei Li, Tao Kong, Lei LI, Yi Wu
Can a robot autonomously learn to design and construct a bridge from varying-sized blocks without a blueprint?
1 code implementation • 9 Apr 2022 • Xin Hu, Zhenyu Wu, Hao-Yu Miao, Siqi Fan, Taiyu Long, Zhenyu Hu, Pengcheng Pi, Yi Wu, Zhou Ren, Zhangyang Wang, Gang Hua
Video action detection (spatio-temporal action localization) is usually the starting point for human-centric intelligent analysis of videos nowadays.
no code implementations • ICLR 2022 • Zihan Zhou, Wei Fu, Bingliang Zhang, Yi Wu
We present Reward-Switching Policy Optimization (RSPO), a paradigm to discover diverse strategies in complex RL environments by iteratively finding novel policies that are both locally optimal and sufficiently different from existing ones.
1 code implementation • 11 Feb 2022 • Runlong Zhou, Yuandong Tian, Yi Wu, Simon S. Du
For a canonical online CO problem, Secretary Problem, we formally prove that distribution shift is reduced exponentially with curriculum learning even if the curriculum is randomly generated.
no code implementations • 3 Jan 2022 • Zhe Zhang, Shiyao Ma, Zhaohui Yang, Zehui Xiong, Jiawen Kang, Yi Wu, Kejia Zhang, Dusit Niyato
This emerging technology relies on sharing ground truth labeled data between Unmanned Aerial Vehicle (UAV) swarms to train a high-quality automatic image recognition model.
1 code implementation • 22 Dec 2021 • Rui Zhao, Jinming Song, Yufeng Yuan, Hu Haifeng, Yang Gao, Yi Wu, Zhongqian Sun, Yang Wei
We study the problem of training a Reinforcement Learning (RL) agent that is collaborative with humans without using any human data.
no code implementations • 13 Dec 2021 • Shusheng Xu, Yichen Liu, Xiaoyu Yi, Siyuan Zhou, Huizi Li, Yi Wu
We present Native Chinese Reader (NCR), a new machine reading comprehension (MRC) dataset with particularly long articles in both modern and classical Chinese.
no code implementations • 13 Dec 2021 • Shusheng Xu, Yancheng Liang, Yunfei Li, Simon Shaolei Du, Yi Wu
A ubiquitous requirement in many practical reinforcement learning (RL) applications, including medical treatment, recommendation system, education and robotics, is that the deployed policy that actually interacts with the environment cannot change frequently.
no code implementations • 12 Dec 2021 • Weilin Liu, Ye Mu, Chao Yu, Xuefei Ning, Zhong Cao, Yi Wu, Shuang Liang, Huazhong Yang, Yu Wang
These scenarios indeed correspond to the vulnerabilities of the under-test driving policies, thus are meaningful for their further improvements.
1 code implementation • NeurIPS 2021 • Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian
We analyze NovelD thoroughly in MiniGrid and found that empirically it helps the agent explore the environment more uniformly with a focus on exploring beyond the boundary.
no code implementations • 17 Nov 2021 • Xiaoteng Zhou, Changli Yu, Xin Yuan, Yi Wu, Haijun Feng, Citong Luo
In the field of deep-sea exploration, sonar is presently the only efficient long-distance sensing device.
1 code implementation • NeurIPS 2021 • Jiayu Chen, Yuanxin Zhang, Yuanfan Xu, Huimin Ma, Huazhong Yang, Jiaming Song, Yu Wang, Yi Wu
We motivate our paradigm through a variational perspective, where the learning objective can be decomposed into two terms: task learning on the current task distribution, and curriculum update to a new task distribution.
no code implementations • 3 Nov 2021 • Yingying Wu, Shusheng Xu, Shing-Tung Yau, Yi Wu
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused an ongoing pandemic infecting 219 million people as of 10/19/21, with a 3. 6% mortality rate.
no code implementations • 26 Oct 2021 • Zhe Zhang, Shiyao Ma, Jiangtian Nie, Yi Wu, Qiang Yan, Xiaoke Xu, Dusit Niyato
In this paper, we present a robust semi-supervised FL system design, where the system aims to solve the problem of data availability and non-IID in FL.
1 code implementation • 12 Oct 2021 • Wenbin Zou, Mingchao Jiang, Yunchen Zhang, Liang Chen, Zhiyong Lu, Yi Wu
On this basis, we reduce the number of up-sampling and down-sampling and design a simple network structure.
Ranked #1 on
Image Deblurring
on RealBlur-R(trained on GoPro)
no code implementations • 12 Oct 2021 • Chao Yu, Xinyi Yang, Jiaxuan Gao, Huazhong Yang, Yu Wang, Yi Wu
In this paper, we extend the state-of-the-art single-agent visual navigation method, Active Neural SLAM (ANS), to the multi-agent setting by introducing a novel RL-based planning module, Multi-agent Spatial Planner (MSP). MSP leverages a transformer-based architecture, Spatial-TeamFormer, which effectively captures spatial relations and intra-agent interactions via hierarchical spatial self-attentions.
no code implementations • 8 Sep 2021 • Shusheng Xu, Xingxing Zhang, Yi Wu, Furu Wei
In this paper, we propose a contrastive learning model for supervised abstractive text summarization, where we view a document, its gold summary and its model generated summaries as different views of the same mean representation and maximize the similarities between them during training.
1 code implementation • 21 Aug 2021 • Weizhe Chen, Zihan Zhou, Yi Wu, Fei Fang
One practical requirement in solving dynamic games is to ensure that the players play well from any decision point onward.
no code implementations • 5 Aug 2021 • Yunfei Li, Tao Kong, Lei LI, Yifeng Li, Yi Wu
In this task, the robot needs to first design a feasible bridge architecture for arbitrarily wide cliffs and then manipulate the blocks reliably to construct a stable bridge according to the proposed design.
no code implementations • SEMEVAL 2021 • Weikang Wang, Yi Wu, Yixiang Liu, Pengyuan Liu
Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase.
no code implementations • 10 Jun 2021 • Minghao Zhang, Pingcheng Jian, Yi Wu, Huazhe Xu, Xiaolong Wang
We address the problem of safely solving complex bimanual robot manipulation tasks with sparse rewards.
no code implementations • 26 Apr 2021 • Longling Zhang, Bochen Shen, Ahmed Barnawi, Shan Xi, Neeraj Kumar, Yi Wu
Under the FL framework and Differentially Private thinking, we propose a FederatedDifferentially Private Generative Adversarial Network (FedDPGAN) to detectCOVID-19 pneumonia for sustainable smart cities.
1 code implementation • 14 Apr 2021 • Li Liu, Xianghao Zhan, Ziheng Duan, Yi Wu, Rumeng Wu, Xiaoqing Guan, Zhan Wang, You Wang, Guang Li
In this study, we classified different origins of three categories of herbal medicines with different feature extraction methods: manual feature extraction, mathematical transformation, deep learning algorithms.
1 code implementation • 7 Apr 2021 • Qingqing Long, Yilun Jin, Yi Wu, Guojie Song
However, the inability of GNNs to model substructures in graphs remains a significant drawback.
no code implementations • 21 Mar 2021 • Guoqing Zhang, Yuhao Chen, Yang Dai, yuhui Zheng, Yi Wu
Due to the inaccurate person detections and pose changes, pedestrian misalignment significantly increases the difficulty of feature extraction and matching.
1 code implementation • ICLR 2021 • Yunfei Li, Yilin Wu, Huazhe Xu, Xiaolong Wang, Yi Wu
We propose a novel learning paradigm, Self-Imitation via Reduction (SIR), for solving compositional reinforcement learning problems.
2 code implementations • ICLR 2021 • Zhenggang Tang, Chao Yu, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Du, Yu Wang, Yi Wu
We propose a simple, general and effective technique, Reward Randomization for discovering diverse strategic policies in complex multi-agent games.
10 code implementations • 2 Mar 2021 • Chao Yu, Akash Velu, Eugene Vinitsky, Jiaxuan Gao, Yu Wang, Alexandre Bayen, Yi Wu
This is often due to the belief that PPO is significantly less sample efficient than off-policy methods in multi-agent systems.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
no code implementations • 21 Jan 2021 • Yuan Fang, Ding Wang, Peng Li, Hang Su, Tian Le, Yi Wu, Guo-Wei Yang, Hua-Li Zhang, Zhi-Guang Xiao, Yan-Qiu Sun, Si-Yuan Hong, Yan-Wu Xie, Huan-Hua Wang, Chao Cao, Xin Lu, Hui-Qiu Yuan, Yang Liu
We report growth, electronic structure and superconductivity of ultrathin epitaxial CoSi2 films on Si(111).
Mesoscale and Nanoscale Physics
no code implementations • 1 Jan 2021 • Shusheng Xu, Simon Shaolei Du, Yi Wu
We initiate the study on deep reinforcement learning problems that require low switching cost, i. e., small number of policy switches during training.
no code implementations • 1 Jan 2021 • Chao Yu, Akash Velu, Eugene Vinitsky, Yu Wang, Alexandre Bayen, Yi Wu
We benchmark commonly used multi-agent deep reinforcement learning (MARL) algorithms on a variety of cooperative multi-agent games.
2 code implementations • 15 Dec 2020 • Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian
In this paper, we analyze the pros and cons of each method and propose the regulated difference of inverse visitation counts as a simple but effective criterion for IR.
no code implementations • 23 Nov 2020 • Peng Li, Baijiang Lv, Yuan Fang, Wei Guo, Zhongzheng Wu, Yi Wu, Cheng-Maw Cheng, Dawei Shen, Yuefeng Nie, Luca Petaccia, Chao Cao, Zhu-An Xu, Yang Liu
Using angle-resolved photoemission spectroscopy (ARPES) and low-energy electron diffraction (LEED), together with density-functional theory (DFT) calculation, we report the formation of charge density wave (CDW) and its interplay with the Kondo effect and topological states in CeSbTe.
Strongly Correlated Electrons Materials Science
2 code implementations • 16 Oct 2020 • Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian
In this work, we propose Collaborative Q-learning (CollaQ) that achieves state-of-the-art performance in the StarCraft multi-agent challenge and supports ad hoc team play.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Shusheng Xu, Xingxing Zhang, Yi Wu, Furu Wei, Ming Zhou
We also find in experiments that our model is less dependent on sentence positions.
no code implementations • 23 Sep 2020 • Junshan Wang, Guojie Song, Yi Wu, Liang Wang
In this paper, we propose a streaming GNN model based on continual learning so that the model is trained incrementally and up-to-date node representations can be obtained at each time step.
1 code implementation • 16 Sep 2020 • Guoqing Zhang, Junchuan Yang, yuhui Zheng, Yi Wu, Sheng-Yong Chen
Finally, we reconstruct the feature extractor to ensure that our model can obtain more richer and robust features.
no code implementations • 16 Apr 2020 • Yujia Zhou, Shumao Pang, Jun Cheng, Yuhang Sun, Yi Wu, Lei Zhao, Yaqin Liu, Zhentai Lu, Wei Yang, Qianjin Feng
In fact, due to the limitation of the receptive field, the 3 x 3 kernel has difficulty in covering the corresponding features at high/original resolution.
1 code implementation • NeurIPS 2020 • Ruihan Yang, Huazhe Xu, Yi Wu, Xiaolong Wang
While training multiple tasks jointly allow the policies to share parameters across different tasks, the optimization problem becomes non-trivial: It remains unclear what parameters in the network should be reused across tasks, and how the gradients from different tasks may interfere with each other.
Ranked #1 on
Meta-Learning
on MT50
1 code implementation • CVPR 2020 • Shiyi Lan, Zhou Ren, Yi Wu, Larry S. Davis, Gang Hua
Object detection is an essential step towards holistic scene understanding.
Ranked #205 on
Object Detection
on COCO test-dev
1 code implementation • ICLR 2020 • Qian Long, Zihan Zhou, Abhibav Gupta, Fei Fang, Yi Wu, Xiaolong Wang
In multi-agent games, the complexity of the environment can grow exponentially as the number of agents increases, so it is particularly challenging to learn good policies when the agent population is large.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
1 code implementation • 19 Jan 2020 • Yi Wang, Yang Yang, Weiguo Zhu, Yi Wu, Xu Yan, Yongfeng Liu, Yu Wang, Liang Xie, Ziyao Gao, Wenjing Zhu, Xiang Chen, Wei Yan, Mingjie Tang, Yuan Tang
Previous database systems extended their SQL dialect to support ML.
1 code implementation • ICLR 2020 • Tonghan Wang, Jianhao Wang, Yi Wu, Chongjie Zhang
We present two exploration methods: exploration via information-theoretic influence (EITI) and exploration via decision-theoretic influence (EDTI), by exploiting the role of interaction in coordinated behaviors of agents.
no code implementations • 4 Oct 2019 • Yi Liu, Jialiang Peng, James J. Q. Yu, Yi Wu
To address this issue, we propose a Privacy-preserving Generative Adversarial Network (PPGAN) model, in which we achieve differential privacy in GANs by adding well-designed noise to the gradient during the model learning procedure.
3 code implementations • ICLR 2020 • Bowen Baker, Ingmar Kanitscheider, Todor Markov, Yi Wu, Glenn Powell, Bob McGrew, Igor Mordatch
Through multi-agent competition, the simple objective of hide-and-seek, and standard reinforcement learning algorithms at scale, we find that agents create a self-supervised autocurriculum inducing multiple distinct rounds of emergent strategy, many of which require sophisticated tool use and coordination.
1 code implementation • ICCV 2019 • Yi Wu, Yuxin Wu, Aviv Tamar, Stuart Russell, Georgia Gkioxari, Yuandong Tian
We introduce a new memory architecture, Bayesian Relational Memory (BRM), to improve the generalization ability for semantic visual navigation agents in unseen environments, where an agent is given a semantic target to navigate towards.
no code implementations • 2 Mar 2019 • Alex Beutel, Jilin Chen, Tulsee Doshi, Hai Qian, Li Wei, Yi Wu, Lukasz Heldt, Zhe Zhao, Lichan Hong, Ed H. Chi, Cristos Goodrow
Recommender systems are one of the most pervasive applications of machine learning in industry, with many services using them to match users to products or information.
no code implementations • 6 Nov 2018 • Yufei Wang, Zheyuan Ryan Shi, Lantao Yu, Yi Wu, Rohit Singh, Lucas Joppa, Fei Fang
Green Security Games (GSGs) have been proposed and applied to optimize patrols conducted by law enforcement agencies in green security domains such as combating poaching, illegal logging and overfishing.
no code implementations • ICLR 2019 • Yi Wu, Yuxin Wu, Aviv Tamar, Stuart Russell, Georgia Gkioxari, Yuandong Tian
Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI.
no code implementations • 28 Jun 2018 • Chaoqiong Fan, Bin Li, Jia Hou, Yi Wu, Weisi Guo, Chenglin Zhao
This allows the system to achieve a smoother and more robust performance by optimizing in an alternate space.
no code implementations • ICML 2018 • Yi Wu, Siddharth Srivastava, Nicholas Hay, Simon Du, Stuart Russell
Despite the recent successes of probabilistic programming languages (PPLs) in AI applications, PPLs offer only limited support for random variables whose distributions combine discrete and continuous elements.
no code implementations • 26 Feb 2018 • Yining Wang, Yi Wu, Simon S. Du
Local polynomial regression (Fan and Gijbels 1996) is an important class of methods for nonparametric density estimation and regression problems.
5 code implementations • ICLR 2018 • Yi Wu, Yuxin Wu, Georgia Gkioxari, Yuandong Tian
To generalize to unseen environments, an agent needs to be robust to low-level variations (e. g. color, texture, object changes), and also high-level variations (e. g. layout changes of the environment).
no code implementations • ICCV 2017 • Congqi Cao, Yifan Zhang, Yi Wu, Hanqing Lu, Jian Cheng
Gesture is a natural interface in interacting with wearable devices such as VR/AR helmet and glasses.
no code implementations • EMNLP 2017 • Yi Wu, David Bamman, Stuart Russell
Adversarial training is a mean of regularizing classification algorithms by generating adversarial noise to the training data.
no code implementations • NeurIPS 2018 • Tongzhou Wang, Yi Wu, David A. Moore, Stuart J. Russell
The learned neural proposals generalize to occurrences of common structural motifs across different models, allowing for the construction of a library of learned inference primitives that can accelerate inference on unseen models with no model-specific training required.
3 code implementations • ICCV 2017 • Yousong Zhu, Chaoyang Zhao, Jinqiao Wang, Xu Zhao, Yi Wu, Hanqing Lu
To fully explore the local and global properties, in this paper, we propose a novel fully convolutional network, named as CoupleNet, to couple the global structure with local parts for object detection.
Ranked #4 on
Object Detection
on PASCAL VOC 2007
76 code implementations • NeurIPS 2017 • Ryan Lowe, Yi Wu, Aviv Tamar, Jean Harb, Pieter Abbeel, Igor Mordatch
We explore deep reinforcement learning methods for multi-agent domains.
Ranked #1 on
SMAC+
on Def_Infantry_sequential
no code implementations • 30 Jun 2016 • Yi Wu, Lei LI, Stuart Russell, Rastislav Bodik
A probabilistic program defines a probability measure over its semantic structures.
no code implementations • LREC 2016 • Junyi Jessy Li, Bridget O{'}Daniel, Yi Wu, Wenli Zhao, Ani Nenkova
We found that the lack of specificity distributes evenly among immediate prior context, long distance prior context and no prior context.
no code implementations • 29 Mar 2016 • Yusuf Bugra Erol, Yi Wu, Lei LI, Stuart Russell
Joint state and parameter estimation is a core problem for dynamic Bayesian networks.
8 code implementations • NeurIPS 2016 • Aviv Tamar, Yi Wu, Garrett Thomas, Sergey Levine, Pieter Abbeel
We introduce the value iteration network (VIN): a fully differentiable neural network with a `planning module' embedded within.
no code implementations • 21 Apr 2015 • Qingshan Liu, Jing Yang, Kaihua Zhang, Yi Wu
Recently, the compressive tracking (CT) method has attracted much attention due to its high efficiency, but it cannot well deal with the large scale target appearance variations due to its data-independent random projection matrix that results in less discriminative features.
no code implementations • 9 Feb 2015 • David Allouche, Christian Bessiere, Patrice Boizumault, Simon de Givry, Patricia Gutierrez, Jimmy H. M. Lee, Kam Lun Leung, Samir Loudni, Jean-Philippe Métivier, Thomas Schiex, Yi Wu
A global cost function is called tractable projection-safe when applying an EPT to it is tractable and does not break the tractability property.
no code implementations • 19 Jan 2015 • Kaihua Zhang, Qingshan Liu, Yi Wu, Ming-Hsuan Yang
In this paper we present that, even without offline training with a large amount of auxiliary data, simple two-layer convolutional networks can be powerful enough to develop a robust representation for visual tracking.
no code implementations • CVPR 2013 • Yi Wu, Jongwoo Lim, Ming-Hsuan Yang
Object tracking is one of the most important components in numerous applications of computer vision.
no code implementations • NeurIPS 2012 • Yi Wu, David P. Wipf
In contrast, for analyses of update rules and sparsity properties of local and global solutions, as well as extensions to more general likelihood models, we can leverage coefficient-space techniques developed for Type I and apply them to Type II.