1 code implementation • 2 Apr 2024 • Haichao Zhang, Yi Xu, HongSheng Lu, Takayuki Shimizu, Yun Fu
By enhancing trajectory prediction accuracy and addressing the challenges of out-of-sight objects, our work significantly contributes to improving the safety and reliability of autonomous driving in complex environments.
no code implementations • 1 Apr 2024 • Bing Xiao, Haichao Zhang, Shijie Zhao, Lu Cao
This brief gives a set of unified Lyapunov stability conditions to guarantee the predefined-time/finite-time stability of a dynamical systems.
no code implementations • 9 Oct 2023 • Haichao Zhang, Yi Xu, HongSheng Lu, Takayuki Shimizu, Yun Fu
In summary, our approach offers a promising solution to the challenges faced by layout sequence and trajectory prediction models in real-world settings, paving the way for utilizing sensor data from mobile phones to accurately predict pedestrian bounding box trajectories.
no code implementations • 13 Aug 2023 • Haichao Zhang, Can Qin, Yu Yin, Yun Fu
This approach can serve as a plug-and-play data generation and augmentation module for existing camouflaged object detection tasks and provides a novel way to introduce more diversity and distributions into current camouflage datasets.
no code implementations • 26 Jun 2023 • Yihan Hu, Kun Li, Pingyuan Liang, Jingyu Qian, Zhening Yang, Haichao Zhang, Wenxin Shao, Zhuangzhuang Ding, Wei Xu, Qiang Liu
This paper presents our 2nd place solution for the NuPlan Challenge 2023.
no code implementations • 2 Jun 2023 • Lingfeng Sun, Haichao Zhang, Wei Xu, Masayoshi Tomizuka
In this work, we investigate the potential of improving multi-task training and also leveraging it for transferring in the reinforcement learning setting.
1 code implementation • 2 Feb 2023 • Haichao Zhang, We Xu, Haonan Yu
With this approach, the policy previously learned offline is fully retained during online learning, thus mitigating the potential issues such as destroying the useful behaviors of the offline policy in the initial stage of online learning while allowing the offline policy participate in the exploration naturally in an adaptive manner.
no code implementations • 5 Nov 2022 • Haichao Zhang, Jiashi Li, Xin Xia, Kuangrong Hao, Xuefeng Xiao
Our improved backbone network can reduce the computational effort while improving the accuracy of the object detection network.
1 code implementation • 21 Oct 2022 • Lingfeng Sun, Haichao Zhang, Wei Xu, Masayoshi Tomizuka
However, the gaps between contents and difficulties of different tasks bring us challenges on both which tasks should share the parameters and what parameters should be shared, as well as the optimization challenges due to parameter sharing.
no code implementations • 20 Mar 2022 • Haichao Zhang, Kuangrong Hao, Witold Pedrycz, Lei Gao, Xuesong Tang, Bing Wei
The high-performance backbone network searched by VTCAS introduces the desirable features of convolutional neural networks into the Transformer architecture while maintaining the benefits of the multi-head attention mechanism.
2 code implementations • 28 Jan 2022 • Haonan Yu, Haichao Zhang, Wei Xu
On the other hand, our large-scale empirical study shows that using entropy regularization alone in policy improvement, leads to comparable or even better performance and robustness than using it in both policy improvement and policy evaluation.
1 code implementation • 28 Jan 2022 • Haonan Yu, Wei Xu, Haichao Zhang
On 12 Safety Gym tasks and 2 safe racing tasks, SEditor obtains much a higher overall safety-weighted-utility (SWU) score than the baselines, and demonstrates outstanding utility performance with constraint violation rates as low as once per 2k time steps, even in obstacle-dense environments.
1 code implementation • ICLR 2022 • Haichao Zhang, Wei Xu, Haonan Yu
GPM can therefore leverage its generated multi-step plans for temporally coordinated exploration towards high value regions, which is potentially more effective than a sequence of actions generated by perturbing each action at single step level, whose consistent movement decays exponentially with the number of exploration steps.
1 code implementation • 20 Jan 2022 • Chenxing Wang, Fang Zhao, Haichao Zhang, Haiyong Luo, Yanjun Qin, Yuchen Fang
To tackle these challenges, we propose a meta learning based framework, MetaTTE, to continuously provide accurate travel time estimation over time by leveraging well-designed deep neural network model called DED, which consists of Data preprocessing module and Encoder-Decoder network module.
no code implementations • 10 Oct 2021 • Haichao Zhang, Youcheng Ben, Weixi Zhang, Tao Chen, Gang Yu, Bin Fu
Recent face reenactment works are limited by the coarse reference landmarks, leading to unsatisfactory identity preserving performance due to the distribution gap between the manipulated landmarks and those sampled from a real person.
no code implementations • 10 Oct 2021 • Haichao Zhang, Gang Yu, Tao Chen, Guozhong Luo
Video creation has been an attractive yet challenging task for artists to explore.
2 code implementations • NeurIPS 2021 • Haonan Yu, Wei Xu, Haichao Zhang
TAAC has two important features: a) persistent exploration, and b) a new compare-through Q operator for multi-step TD backup, specially tailored to the action repetition scenario.
no code implementations • 23 Mar 2021 • Haichao Zhang, Kuangrong Hao, Lei Gao, Xuesong Tang, Bing Wei
At the stage of block-level search, a relaxation method based on the gradient is proposed, using an enhanced gradient to design high-performance and low-complexity blocks.
no code implementations • 21 Dec 2020 • Haichao Zhang, Kuangrong Hao, Lei Gao, Bing Wei, Xuesong Tang
Deep neural networks (DNNs) have achieved remarkable success in computer vision; however, training DNNs for satisfactory performance remains challenging and suffers from sensitivity to empirical selections of an optimization algorithm for training.
no code implementations • 25 Sep 2019 • Haichao Zhang, Wei Xu
We propose a simple approach for adversarial training.
3 code implementations • NeurIPS 2019 • Haichao Zhang, Jian-Yu Wang
We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks.
no code implementations • ICCV 2019 • Haichao Zhang, Jian-Yu Wang
Object detection is an important vision task and has emerged as an indispensable component in many vision system, rendering its robustness as an increasingly important performance factor for practical applications.
no code implementations • 24 Jul 2019 • Haichao Zhang, Jian-Yu Wang
In this paper, we propose a joint adversarial training method that incorporates both spatial transformation-based and pixel-value based attacks for improving model robustness.
no code implementations • ICLR 2019 • Liqun Chen, Yizhe Zhang, Ruiyi Zhang, Chenyang Tao, Zhe Gan, Haichao Zhang, Bai Li, Dinghan Shen, Changyou Chen, Lawrence Carin
Sequence-to-sequence models are commonly trained via maximum likelihood estimation (MLE).
1 code implementation • ICCV 2019 • Jianyu Wang, Haichao Zhang
To generate the adversarial image, we use one-step targeted attack with the target label being the most confusing class.
1 code implementation • NeurIPS 2018 • Liqun Chen, Shuyang Dai, Chenyang Tao, Dinghan Shen, Zhe Gan, Haichao Zhang, Yizhe Zhang, Lawrence Carin
However, the discrete nature of text hinders the application of GAN to text-generation tasks.
1 code implementation • 22 May 2018 • Haonan Yu, Xiaochen Lian, Haichao Zhang, Wei Xu
Recently there has been a rising interest in training agents, embodied in virtual environments, to perform language-directed tasks by deep reinforcement learning.
1 code implementation • ACL 2018 • Haichao Zhang, Haonan Yu, Wei Xu
Building intelligent agents that can communicate with and learn from humans in natural language is of great value.
2 code implementations • ICLR 2018 • Haonan Yu, Haichao Zhang, Wei Xu
We build a virtual agent for learning language in a 2D maze-like world.
no code implementations • 20 Dec 2017 • Ding Liu, Bowen Cheng, Zhangyang Wang, Haichao Zhang, Thomas S. Huang
Visual recognition under adverse conditions is a very important and challenging problem of high practical value, due to the ubiquitous existence of quality distortions during image acquisition, transmission, or storage.
1 code implementation • 28 May 2017 • Haichao Zhang, Haonan Yu, Wei Xu
One of the long-term goals of artificial intelligence is to build an agent that can communicate intelligently with human in natural language.
no code implementations • 28 Mar 2017 • Haonan Yu, Haichao Zhang, Wei Xu
We believe that our results provide some preliminary insights on how to train an agent with similar abilities in a 3D environment.
no code implementations • CVPR 2015 • Haichao Zhang, Jianchao Yang
The proposed method effectively leverages the information distributed across multiple video frames due to camera motion, jointly estimating the motion between consecutive frames and blur within each frame.
no code implementations • NeurIPS 2014 • Haichao Zhang, Jianchao Yang
The presence of noise and small scale structures usually leads to large kernel estimation errors in blind image deblurring empirically, if not a total failure.
no code implementations • CVPR 2014 • Haichao Zhang, Lawrence Carin
Registering multiple blurry images is a challenging task due to the presence of blur while deblurring of multiple blurry images requires accurate alignment, leading to an intrinsically coupled problem.
no code implementations • NeurIPS 2013 • Haichao Zhang, David Wipf
Typical blur from camera shake often deviates from the standard uniform convolutional assumption, in part because of problematic rotations which create greater blurring away from some unknown center point.
no code implementations • 17 Jun 2013 • Haichao Zhang, David Wipf
Typical blur from camera shake often deviates from the standard uniform convolutional script, in part because of problematic rotations which create greater blurring away from some unknown center point.
no code implementations • CVPR 2013 • Haichao Zhang, David Wipf, Yanning Zhang
This paper presents a robust algorithm for estimating a single latent sharp image given multiple blurry and/or noisy observations.
no code implementations • 10 May 2013 • David Wipf, Haichao Zhang
Blind deconvolution involves the estimation of a sharp signal or image given only a blurry observation.