qiang fang

Prof. qiang fang


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 April 2021 in CAAI Transactions on Intelligence Technology
Verified
Journal Article
Open access
PDF file
QFqiang fang
qiang fang
XXXin Xu
Xin Xu
XWXitong Wang
Xitong Wang
YZYujun Zeng
Yujun Zeng
Here, the challenges of sample efficiency and navigation performance in deep reinforcement learning for visual navigation are focused and a deep imitation reinforcement learning approach is proposed. Our contributions are mainly three folds: first, a framework combining imitation learning with deep reinforcement learning is presented, which enables a robot to learn a stable navigation policy faster in the target‐driven navigation task. Second, the surrounding images is taken as the observation instead of sequential images, which can improve the navigation performance for more information. Moreover, a simple yet efficient template matching method is adopted to determine the stop action, making the system more practical. Simulation experiments in the AI‐THOR environment show that the proposed approach outperforms previous end‐to‐end deep reinforcement learning approaches, which demonstrate the effectiveness and efficiency of our approach.

11 May 2023 in Journal of Colloid and Interface Science
Verified
Journal Article
Closed access
TLTian Lu
Tian Lu
DZDazhong Zhong
Dazhong Zhong
TZTao Zhao
Tao Zhao
YLYi Liu
Yi Liu
LHLu Hao
Lu Hao
QZQiang Zhao
Qiang Zhao

21 July 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
SSShuohao Shi
Shuohao Shi
QFqiang fang
qiang fang
XXXin Xu
Xin Xu
DDDezun Dong
Dezun Dong
Tiny object detection is increasingly crucial in the fields such as remote sensing, traffic monitoring, and robotics. Inspired by human visual perception, attention mechanism has become a widely used method for enhancing object detection performance. While existing attention mechanisms have significantly advanced general object detection performance, they often fall short in adapting to the characteristics in tiny object datasets, including huge object size variations and concentrated distributions. In detailed, most current attention mechanisms rely on convolutional or linear layers with fixed receptive fields to compute attention vectors. Some methods attempt to enlarge the receptive fields by using multiscale structures, but they often simply sum feature maps, leading to information interference and increased computational costs. To address these issues, we propose a novel Multiscale Gaussian Attention Mechanism (MGAM). This mechanism integrates multiscale receptive fields with dynamic feature weighting and a Gaussian attention module, replacing traditional convolutional layers to reduce training and inference overhead. In additional, our mechanism can be easily embedded into various detectors without any hyperparameters. Extensive experiments on six object detection datasets demonstrate the effectiveness and robustness of our method. Code is available at: https://github.com/cszzshi/MGAM.

29 November 2024 in IEEE Transactions on Cognitive and Developmental Systems
Verified
Journal Article
Closed access
YLYixing Lan
Yixing Lan
HGHao Gao
Hao Gao
XXXin Xu
Xin Xu
QFqiang fang
qiang fang
YZYujun Zeng
Yujun Zeng
Multi-agent reinforcement learning (MARL) has received increasing attention and been used to solve cooperative multi-agent decision-making and learning control tasks. However, the high complexity of the joint action space and the non-stationary learning process are two major problems that negatively impact on the sample efficiency and solution quality of MARL. To this end, this paper proposes a novel approach named Sequential Multi-Agent reinforcement learning with Role assignment using Transformer (SMART). By learning the effects of different actions on state transitions and rewards, SMART realizes the action abstraction of the original action space and the adaptive role cognitive modeling of multi-agent, which reduces the complexity of the multi-agent exploration and learning process. Meanwhile, SMART uses causal Transformer networks to update role assignment policy and action selection policy sequentially, alleviating the influence of non-stationary multi-agent policy learning. The convergence characteristic of SMART is theoretically analyzed. Extensive experiments on the challenging Google Football and StarCraft Multi-Agent Challenge are conducted, demonstrating that compared with mainstream MARL algorithms such as MAT and HAPPO, SMART achieves a new state-of-the-art performance. Meanwhile, the learned policies through SMART have good generalization ability when the number of agents changes.

1 January 2021 in Computational Intelligence and Neuroscience
Verified
Journal Article
Open access
PDF file
YZYichuan Zhang
Yichuan Zhang
YLYixing Lan
Yixing Lan
QFqiang fang
qiang fang
XXXin Xu
Xin Xu
JLJunxiang Li
Junxiang Li
YZYujun Zeng
Yujun Zeng
Reinforcement learning from demonstration (RLfD) is considered to be a promising approach to improve reinforcement learning (RL) by leveraging expert demonstrations as the additional decision‐making guidance. However, most existing RLfD methods only regard demonstrations as low‐level knowledge instances under a certain task. Demonstrations are generally used to either provide additional rewards or pretrain the neural network‐based RL policy in a supervised manner, usually resulting in poor generalization capability and weak robustness performance. Considering that human knowledge is not only interpretable but also suitable for generalization, we propose to exploit the potential of demonstrations by extracting knowledge from them via Bayesian networks and develop a novel RLfD method called Reinforcement Learning from demonstration via Bayesian Network‐based Knowledge (RLBNK). The proposed RLBNK method takes advantage of node influence with the Wasserstein distance metric (NIW) algorithm to obtain abstract concepts from demonstrations and then a Bayesian network conducts knowledge learning and inference based on the abstract data set, which will yield the coarse policy with corresponding confidence. Once the coarse policy’s confidence is low, another RL‐based refine module will further optimize and fine‐tune the policy to form a (near) optimal hybrid policy. Experimental results show that the proposed RLBNK method improves the learning efficiency of corresponding baseline RL algorithms under both normal and sparse reward settings. Furthermore, we demonstrate that our RLBNK method delivers better generalization capability and robustness than baseline methods.

16 December 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Open access
TZTong Zhao
Tong Zhao
QFqiang fang
qiang fang
XXXin Xu
Xin Xu
Oriented object detection, which aims to detect multi-oriented objects, is a fundamental task for visual analysis in complex scenarios, such as aerial images. However, pow4 erful detection performance relies on abundant and accurate annotations. Therefore, semi-supervised oriented object detection, which utilizes unlabeled data to improve performance, is a promising method to address this problem. In this work, we explore Dense Pseudo-Label (DPL), which directly selects pseudo labels from the original output of the teacher model without any complicated post-processing steps, and expose the shortcomings of existing methods. Through analysis, we identify that the imbalance between obtaining potential positive samples and removing the interference of inaccurate pseudo labels hinders the effectiveness of DPL. To further improve DPL efficiency, we propose Denser Teacher, a new semi-supervised oriented object detection method. In this method, we design a simple yet effective adaptive mechanism called global dynamic k estimation to guide the selection of DPLs in densely-distributed scenes. Additionally, to improve scale adaptation, we introduce dense multi-scale learning for DPL, where DPLs from different scales are utilized to bridge the scale gap. We conduct extensive experiments on several benchmarks to demonstrate the effectiveness of our proposed method in leveraging unlabeled data for performance improve24 ment. Our code will be available at https://github.com/Haru25zt/DenserTeacher.