Qiguang Miao

Dr. Qiguang Miao

School of Computer Science and Technology, Xidian University, Xi’an 710071, China
orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
28 September 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
XWXu Wang
Xu Wang
SWSen Wang
Sen Wang
XLXingxing Liang
Xingxing Liang
DZDawei Zhao
Dawei Zhao
JHJincai Huang
Jincai Huang
Qiguang MiaoQiguang Miao
Qiguang Miao
Deep reinforcement learning (DRL) integrates the feature representation ability of deep learning with the decision-making ability of reinforcement learning so that it can achieve powerful end-to-end learning control capabilities. In the past decade, DRL has made substantial advances in many tasks that require perceiving high-dimensional input and making optimal or near-optimal decisions. However, there are still many challenging problems in the theory and applications of DRL, especially in learning control tasks with limited samples, sparse rewards, and multiple agents. Researchers have proposed various solutions and new theories to solve these problems and promote the development of DRL. In addition, deep learning has stimulated the further development of many subfields of reinforcement learning, such as hierarchical reinforcement learning (HRL), multiagent reinforcement learning, and imitation learning. This article gives a comprehensive overview of the fundamental theories, key algorithms, and primary research domains of DRL. In addition to value-based and policy-based DRL algorithms, the advances in maximum entropy-based DRL are summarized. The future research topics of DRL are also analyzed and discussed.

18 February 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
Yue WuYue Wu
Yue Wu
JLJiaheng Li
Jiaheng Li
YYYongzhe Yuan
Yongzhe Yuan
Kai QinKai Qin
Kai Qin
Qiguang MiaoQiguang Miao
Qiguang Miao
Maoguo GongMaoguo Gong
Maoguo Gong
Change detection based on heterogeneous images, such as optical images and synthetic aperture radar images, is a challenging problem because of their huge appearance differences. To combat this problem, we propose an unsupervised change detection method that contains only a convolutional autoencoder (CAE) for feature extraction and the commonality autoencoder for commonalities exploration. The CAE can eliminate a large part of redundancies in two heterogeneous images and obtain more consistent feature representations. The proposed commonality autoencoder has the ability to discover common features of ground objects between two heterogeneous images by transforming one heterogeneous image representation into another. The unchanged regions with the same ground objects share much more common features than the changed regions. Therefore, the number of common features can indicate changed regions and unchanged regions, and then a difference map can be calculated. At last, the change detection result is generated by applying a segmentation algorithm to the difference map. In our method, the network parameters of the commonality autoencoder are learned by the relevance of unchanged regions instead of the labels. Our experimental results on five real data sets demonstrate the promising performance of the proposed framework compared with several existing approaches.

22 January 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
XLXiaocong Lu
Xiaocong Lu
JJJian Ji
Jian Ji
ZXZhiqi Xing
Zhiqi Xing
Qiguang MiaoQiguang Miao
Qiguang Miao
Object detection is a basic topic in the field of remote sensing. However, remote sensing images usually suffer in complicated backgrounds, object scale variations, and small objects, which make remote sensing object detection still difficult. Although the existing two-stage methods have higher accuracy, their detection speed is slow. While the one-stage object detection algorithms such as single-shot detector (SSD) and YOLO, although they can achieve real-time detection, they have poor detection performance, especially for small objects. In this article, in order to further improve the remote sensing object detection performance of one-stage methods, we propose an end-to-end network named attention and feature fusion SSD. First, a multilayer feature fusion structure is designed to enhance the semantic information of the shallow features. Next, a dual-path attention module is introduced to screen the feature information. This module uses spatial attention and channel attention to suppress the background noise and highlight the key feature. Then, the feature representation ability of the network is further enhanced by a multiscale receptive field module. Finally, the loss function is optimized to alleviate the imbalance between the positive and negative samples. The experimental results on the DOTA and NWPU VHR-10 data sets verify the effectiveness of our method.

19 October 2022 in IEEE Transactions on Evolutionary Computation
Verified
Journal Article
Closed access
Yue WuYue Wu
Yue Wu
HDHangqi Ding
Hangqi Ding
Maoguo GongMaoguo Gong
Maoguo Gong
Kai QinKai Qin
Kai Qin
Wenping MaWenping Ma
Wenping Ma
KTKay Chen Tan
Kay Chen Tan
Point cloud registration is an important task in computer vision, where the goal is to estimate a transformation to align a pair of point clouds. Most of the existing registration methods face the problems of poor robustness and getting stuck in local optima. Evolutionary multitasking is an effective paradigm to enhance global search capability and improve convergence characteristics through knowledge transfer across multiple related tasks. Inspired by evolutionary multitasking, this paper proposes a multiform optimization approach through evolutionary multitasking for solving the point cloud registration problems. we first construct two related registration tasks with different functional landscapes to form a multiform optimization problem. Compared with methods that only focus on a single registration attribute, the two proposed tasks focus on robustness and precision of registration, respectively. Then, a new two-stage bidirectional knowledge transfer strategy is presented, which can implement efficient knowledge transfer among two related tasks. Finally, both simulations and real experiments show the power of our method. The proposed method is robust to noise, outliers, and partial overlaps, and is effective in multiple real registration scenarios, such as object registration, scene reconstruction, simultaneous localization and mapping.

16 January 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
Yue WuYue Wu
Yue Wu
XHXidao Hu
Xidao Hu
YZYue Zhang
Yue Zhang
Maoguo GongMaoguo Gong
Maoguo Gong
Wenping MaWenping Ma
Wenping Ma
Qiguang MiaoQiguang Miao
Qiguang Miao
Rigid registration is a transformation estimation problem between two point clouds. The two point clouds captured may partially overlap owing to different viewpoints and acquisition times. Some previous correspondence matching based methods utilize an encoder-decoder network to carry out partial-to-partial registration task and adopt a skip-connection structure to convey information between the encoder and decoder. However, equally revisiting them with skip-connection may introduce the information redundancy, and limit the feature learning ability of the entire network. To address these problems, we propose a skip-attention based correspondence filtering network ( SACF-Net ) for point cloud registration. A novel feature interaction mechanism is designed to utilize both low-level geometric information and high-level context-aware information to enhance the original pointwise matching map. Additionally, a skip-attention based correspondence filtering method is proposed to selectively revisits features in the encoder at different resolutions, allowing the decoder to extract high-quality correspondences within overlapping regions. We conduct comprehensive experiments on indoor and outdoor scene datasets, and the results show that the proposed SACF-Net yields unprecedented performance improvements.

16 November 2023 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
YYYongzhe Yuan
Yongzhe Yuan
Yue WuYue Wu
Yue Wu
XFXiaolong Fan
Xiaolong Fan
Maoguo GongMaoguo Gong
Maoguo Gong
Wenping MaWenping Ma
Wenping Ma
Qiguang MiaoQiguang Miao
Qiguang Miao
We explore the effect of geometric structure descriptors on extracting reliable correspondences and obtaining accurate registration for point cloud registration. The point cloud registration task involves the estimation of rigid transformation motion in unorganized point cloud, hence it is crucial to capture the contextual features of the geometric structure in point cloud. Recent coordinates-only methods ignore numerous geometric information in the point cloud which weaken ability to express the global context. We propose Enhanced Geometric Structure Transformer to learn enhanced contextual features of the geometric structure in point cloud and model the structure consistency between point clouds for extracting reliable correspondences, which encodes three explicit enhanced geometric structures and provides significant cues for point cloud registration. More importantly, we report empirical results that Enhanced Geometric Structure Transformer can learn meaningful geometric structure features using none of the following: (i) explicit positional embeddings, (ii) additional feature exchange module such as cross-attention, which can simplify network structure compared with plain Transformer. Extensive experiments on the synthetic dataset and real-world datasets illustrate that our method can achieve competitive results.