Search Results for author: Haichao Zhang

Found 40 papers, 16 papers with code

FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning

1 code implementation2 Jun 2024 Yuwei Fu, Haichao Zhang, Di wu, Wei Xu, Benoit Boulet

In this work, we investigate how to leverage pre-trained visual-language models (VLM) for online Reinforcement Learning (RL).

reinforcement-learning Reinforcement Learning (RL)

OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising

1 code implementation CVPR 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.

Autonomous Driving Decision Making +2

Unified Predefined-time Stability Conditions of Nonlinear Systems with Lyapunov Analysis

no code implementations1 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.

Layout Sequence Prediction From Noisy Mobile Modality

no code implementations9 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.

Autonomous Driving Denoising +1

Camouflaged Image Synthesis Is All You Need to Boost Camouflaged Detection

no code implementations13 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.

Image Generation Object +2

Efficient Multi-Task and Transfer Reinforcement Learning with Parameter-Compositional Framework

no code implementations2 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.

reinforcement-learning Transfer Reinforcement Learning

Policy Expansion for Bridging Offline-to-Online Reinforcement Learning

1 code implementation2 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.

reinforcement-learning Reinforcement Learning (RL)

Multi-Objective Evolutionary for Object Detection Mobile Architectures Search

no code implementations5 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.

Image Classification Neural Architecture Search +3

PaCo: Parameter-Compositional Multi-Task Reinforcement Learning

1 code implementation21 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.

reinforcement-learning Reinforcement Learning (RL)

Vision Transformer with Convolutions Architecture Search

no code implementations20 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.

Image Classification object-detection +2

Do You Need the Entropy Reward (in Practice)?

2 code implementations28 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.

Towards Safe Reinforcement Learning with a Safety Editor Policy

1 code implementation28 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.

2k reinforcement-learning +2

Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning

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.

reinforcement-learning Reinforcement Learning (RL)

Fine-Grained Trajectory-based Travel Time Estimation for Multi-city Scenarios Based on Deep Meta-Learning

1 code implementation20 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.

Decoder Meta-Learning +1

Fine-grained Identity Preserving Landmark Synthesis for Face Reenactment

no code implementations10 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.

Face Reenactment

Sketch Me A Video

no code implementations10 Oct 2021 Haichao Zhang, Gang Yu, Tao Chen, Guozhong Luo

Video creation has been an attractive yet challenging task for artists to explore.

TAAC: Temporally Abstract Actor-Critic for Continuous Control

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.

Continuous Control

Enhanced Gradient for Differentiable Architecture Search

no code implementations23 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.

Classification General Classification +2

Optimizing Deep Neural Networks through Neuroevolution with Stochastic Gradient Descent

no code implementations21 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.

Defense Against Adversarial Attacks Using Feature Scattering-based 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.

Towards Adversarially Robust Object Detection

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.

Multi-Task Learning Object +2

Joint Adversarial Training: Incorporating both Spatial and Pixel Attacks

no code implementations24 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.

Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks

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.

Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents

1 code implementation22 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.

reinforcement-learning Reinforcement Learning (RL) +2

Enhance Visual Recognition under Adverse Conditions via Deep Networks

no code implementations20 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.

Data Augmentation Image Restoration +3

Listen, Interact and Talk: Learning to Speak via Interaction

1 code implementation28 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.


A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment

no code implementations28 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.

Language Acquisition Navigate +1

Intra-Frame Deblurring by Leveraging Inter-Frame Camera Motion

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.


Scale Adaptive Blind Deblurring

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.

Blind Image Deblurring Image Deblurring

Multi-Shot Imaging: Joint Alignment, Deblurring and Resolution-Enhancement

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.

Deblurring Image Restoration

Non-Uniform Camera Shake Removal Using a Spatially-Adaptive Sparse Penalty

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.

Bayesian Inference Deblurring

Non-Uniform Blind Deblurring with a Spatially-Adaptive Sparse Prior

no code implementations17 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.

Bayesian Inference Deblurring

Multi-image Blind Deblurring Using a Coupled Adaptive Sparse Prior

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.


Revisiting Bayesian Blind Deconvolution

no code implementations10 May 2013 David Wipf, Haichao Zhang

Blind deconvolution involves the estimation of a sharp signal or image given only a blurry observation.

Cannot find the paper you are looking for? You can Submit a new open access paper.