Rongxin Jiang

Dr. Rongxin Jiang


Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
25 November 2024 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
KLKai Liu
Kai Liu
ZFZhihang Fu
Zhihang Fu
SJSheng Jin
Sheng Jin
ZCZe Chen
Ze Chen
FZFan Zhou
Fan Zhou
JYJieping Ye
Jieping Ye
Enlarging input images is a straightforward and effective approach to promote small object detection. However, simple image enlargement is significantly expensive on both computations and GPU memory. In fact, small objects are usually sparsely distributed and locally clustered. Therefore, massive feature extraction computations are wasted on the non-target background area of images. Recent works have tried to pick out target-containing regions using an extra network and perform conventional object detection, but the newly introduced computation limits their final performance. In this paper, we propose to reuse the detector’s backbone to conduct feature-level object-seeking and patch-slicing, which can avoid redundant feature extraction and reduce the computation cost. Incorporating with a sparse detection head, we are able to detect small objects on high-resolution inputs (e.g., 1080P or larger) for superior performance. The resulting Efficient Small Object Detection (ESOD) approach is a generic framework, which can be applied to both CNN- and ViT-based detectors to save the computation and GPU memory costs. Extensive experiments demonstrate the efficacy and efficiency of our method. In particular, our method consistently surpasses the SOTA detectors by a large margin (e.g., 8% gains on AP) on the representative VisDrone, UAVDT, and TinyPerson datasets. Code will be made public soon.

25 November 2019 in IEEE Access
Verified
Journal Article
Open access
HCHaonan Chen
Haonan Chen
YCYaowu Chen
Yaowu Chen
XTXiang Tian
Xiang Tian
RJRongxin Jiang
Rongxin Jiang
In consideration of secure and convenient, face gains increasing attention in variety of fields during the past decades. Since human face is most accessible from our daily life and preserves the richest information, face based biometric systems are widely used in person authentication applications. However, face recognition systems are always challenged by face spoofing attacks. Although, researchers have proposed many face spoofing detection methods, which have achieved great performances, we aim to develop a method to counter face spoofing, which combines the face detection stage and face spoofing detection stage together. In this paper, we design face anti-spoofing region-based convolutional neural network (FARCNN), based on improved Faster region-based convolutional neural network (R-CNN) framework. Motivated by face detection, we regard the face spoofing detection as a three-way classification to distinguish real face, fake face and background. We extend the typical Faster R-CNN scheme by optimizing several important strategies, including roi-pooling feature fusion and adding Crystal Loss function to the original multi-task loss function. In addition, an improved Retinex based LBP is presented to handle the different illumination conditions in face spoofing detection. Finally, these two detectors are further cascaded and achieve promising performances on the benchmark databases: CASIA-FASD, REPLAY-ATTACK and OULU-NPU. Besides, for the purpose of verifying the generalization capacity of the proposed cascade detector, we perform experiments on cross-databases and the results testify the effectiveness of our proposed method.

25 November 2013 in IEEE Journal of Oceanic Engineering
Verified
Journal Article
Closed access
YHYeqiang Han
Yeqiang Han
XTXiang Tian
Xiang Tian
FZFan Zhou
Fan Zhou
RJRongxin Jiang
Rongxin Jiang
YCYaowu Chen
Yaowu Chen
Real-time 3-D acoustical imaging technique is a key advance to broaden the scope and enhance the feasibility of underwater missions. In this paper, a real-time 3-D underwater acoustical imaging system to handle the actual tasks under a narrowband excitation is presented. The system consists of three parts: a transmitter, a receiving hydrophone array, and a signal processor. In this system, a distributed and parallel subarray (DPS) beamforming algorithm is proposed to process the acquired signals from a scene placed in the far field. The DPS beamforming algorithm is an approximate method for the sonar signal processing with an advantageous computational efficiency. The direct method (DM) and fast Fourier transform (FFT) beamforming are compared with DPS beamforming for the memory and computational requirements. Based on this algorithm, a prototype was developed, which has been extensively employed in the lake and sea trials. The trials demonstrate that the system can achieve the 3-D imaging of the scene and meet the real-time requirement of the underwater operations.

6 March 2020 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SYShangjie Yao
Shangjie Yao
YCYaowu Chen
Yaowu Chen
XTXiang Tian
Xiang Tian
RJRongxin Jiang
Rongxin Jiang
SMShuhao Ma
Shuhao Ma
Pneumonia is a disease that develops rapidly and seriously threatens the survival and health of human beings. At present, the computer-aided diagnosis (CAD) of pneumonia is mostly based on binary classification algorithms that cannot provide doctors with location information. To solve this problem, this study proposes an end-to-end highly efficient algorithm for the detection of pneumonia based on a convolutional neural network—Pneumonia Yolo (PYolo). This algorithm is an improved version of the Yolov3 algorithm for X-ray image data of the lungs. Dilated convolution and an attention mechanism are used to improve the detection results of pneumonia lesions. In addition, double K-means is used to generate an anchor box to improve the localization accuracy. The algorithm obtained 46.84 mean average precision (mAP) on the X-ray image dataset provided by the Radiological Society of North America (RSNA), surpassing other detection algorithms. Thus, this study proposes an improved algorithm that can provide doctors with location information on lesions for the detection of pneumonia.

23 December 2020 in IEEE Antennas and Wireless Propagation Letters
Verified
Journal Article
Closed access
ZLZhenwei Lin
Zhenwei Lin
YCYaowu Chen
Yaowu Chen
XLXuesong Liu
Xuesong Liu
RJRongxin Jiang
Rongxin Jiang
BSBinjian Shen
Binjian Shen
Array diagnosis is an important tool for detecting and correcting array antennas failures. In this letter, a high-precision planar array diagnosis method based on the Bayesian compressive sensing theory is proposed. The model of a near-field signal with a spherical wavefront is used to acquire the measured data. Then, the difference between the beam pattern of the reference array and the array under test is obtained. The array diagnosis problem involves finding the difference between the weights of the reference and of the array under test with known differences between patterns. This problem is reformulated in a Bayesian compressive sensing framework and can be efficiently solved using a fast relevance vector machine. Numerical results confirm the superiority of the proposed method in terms of diagnostic accuracy and computational efficiency than those in previous studies.

30 January 2024 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
XYXin Ye
Xin Ye
RJRongxin Jiang
Rongxin Jiang
XTXiang Tian
Xiang Tian
RZRui Zhang
Rui Zhang
YCYaowu Chen
Yaowu Chen
This letter proposes a novel method for effectively utilizing multiple teachers in feature-based knowledge distillation. Our method involves a multi-teacher feature ensemble module for generating a robust feature ensemble and a student-teacher mapping module for bridging the student feature and ensemble feature. In addition, we utilize separate optimization, where the student's feature extractor is optimized under distillation supervision while its classifier is obtained through classifier reconstruction. We evaluate our method on the CIFAR-100, ImageNet and MS-COCO datasets, and the experimental results demonstrate its effectiveness.