Yang Zhao

Yang Zhao

Auto-generated profile, based on publicly available information

Yang Zhao

National university of defense technology, Changsha, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
11 May 2020 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
XTXiaoguang Tu
Xiaoguang Tu
Jian ZhaoJian Zhao
Jian Zhao
MXMei Xie
Mei Xie
ZJZihang Jiang
Zihang Jiang
ABAkshaya Balamurugan
Akshaya Balamurugan
JFJiashi Feng
Jiashi Feng
3D face reconstruction from a single image is an important task in many multimedia applications. Recent works typically learn a CNN-based 3D face model that regresses coefficients of a 3D Morphable Model (3DMM) from 2D images to perform 3D face reconstruction. However, the shortage of training data with 3D annotations considerably limits performance of these methods. To alleviate this issue, we propose a novel 2D-Assisted Learning (2DAL) method that can effectively use “in the wild” 2D face images with noisy landmark information to substantially improve 3D face model learning. Specifically, taking the sparse 2D facial landmark heatmaps as additional information, 2DAL introduces four novel self-supervision schemes that view the 2D landmark and 3D landmark prediction as a self-mapping process, including the landmark self-prediction consistency for 2D and 3D faces respectively, cycle-consistency over the 2D landmark prediction and self-critic over the predicted 3DMM coefficients based on landmark prediction. Using these four self- supervision schemes, 2DAL significantly relieves the demands for the the conventional paired 2D-to-3D annotations and gives much higher-quality 3D face models without requiring any additional 3D annotations. Experiments on AFLW2000-3D, AFLW-LFPA and Florence benchmarks show that our method outperforms state-of-the-arts for both 3D face reconstruction and dense face alignment by a large margin.

25 April 2022 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Open access
DZDavid Zimmerer
David Zimmerer
PFPeter M. Full
Peter M. Full
FIFabian Isensee
Fabian Isensee
PJPaul Jager
Paul Jager
TATim Adler
Tim Adler
KMKlaus Maier-Hein
Klaus Maier-Hein
Detecting Out-of-Distribution (OoD) data is one of the greatest challenges in safe and robust deployment of machine learning algorithms in medicine. When the algorithms encounter cases that deviate from the distribution of the training data, they often produce incorrect and over-confident predictions. OoD detection algorithms aim to catch erroneous predictions in advance by analysing the data distribution and detecting potential instances of failure. Moreover, flagging OoD cases may support human readers in identifying incidental findings. Due to the increased interest in OoD algorithms, benchmarks for different domains have recently been established. In the medical imaging domain, for which reliable predictions are often essential, an open benchmark has been missing. We introduce the Medical-Out-Of-Distribution-Analysis-Challenge (MOOD) as an open, fair, and unbiased benchmark for OoD methods in the medical imaging domain. The analysis of the submitted algorithms shows that performance has a strong positive correlation with the perceived difficulty, and that all algorithms show a high variance for different anomalies, making it yet hard to recommend them for clinical practice. We also see a strong correlation between challenge ranking and performance on a simple toy test set, indicating that this might be a valuable addition as a proxy dataset during anomaly detection algorithm development.

25 October 2021 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YXYunsheng Xiong
Yunsheng Xiong
KXKele Xu
Kele Xu
YDYong Dou
Yong Dou
YZYang Zhao
Yang Zhao
ZGZikai Gao
Zikai Gao
Semisupervised learning (SSL), such as FixMatch, has been successfully applied to remote sensing scene classification to relieve the burden of data annotation. However, in some extreme settings, only very few samples available, e.g., one to ten labels per remote sensing scene, can be used. When meeting this “few-shot” scenario, the deep model may be overfitting and prone to generate confusing predictions due to the lack of labels and strong augmentation-based perturbations. Thus, the prediction’s diversity may collapse, and the discriminability exceeds the reasonable interval. How to improve the performance of few-shot learning is underexplored for the remote sensing scene classification in previous studies. In this article, we present a novel framework for the task by utilizing the improved FixMatch and the weighted nuclear-norm regularization (WNNR). Specifically, we regularize the prediction matrix by exploiting the nuclear-norm, which is an approximation of the matrix rank and a relaxed boundary for the Shannon entropy. We further provide two weighting schemes to improve the nuclear-norm-based regularization. First, the random-weighting scheme for nuclear-norm (RWNNR) is proposed based on the Dirichlet distribution to improve the model’s generalization. Second, we present the self-weighting scheme (SWNNR) to weight the singular values according to singular values themselves and adjust the relaxed degree for the boundary between the nuclear-norm and the Shannon entropy. Maximizing the weighted nuclear-norm can improve the prediction diversity and optimize the prediction discriminability simultaneously. Combining the advantages of SSL and the aforementioned improvements, we can reliably classify the remote sensing scene image with very limited annotated datasets. To empirically demonstrate the proposed method’s effectiveness, we comprehensively evaluate the method on three publicly available benchmark datasets. The results show that the proposed method outperforms the baseline methods by a large margin and achieves superior performance on all three datasets. Our method can be an effective alternative to metalearning in few-shot scene classification, with the advantage lying in the competitive performance and the absence of metatraining stage associated with a large number of labels.

18 May 2020 in IEEE Access
Verified
Journal Article
Open access
YZYang Zhao
Yang Zhao
YDYong Dou
Yong Dou
Human video prediction is still a challenging problem due to the uncertainty of future actions and complexity of frame details. Recent methods tackle this problem in two steps: firstly to forecast future human poses from the initial ones, and then to generate realistic frames conditioned on predicted poses. Following this framework, we propose a novel Graph Convolutional Network (GCN) based pose predictor to comprehensively model human body joints and forcast their positions holistically, and also a stacked generative model with a temporal discriminator to iteratively refine the quality of the generated videos. The GCN based pose predictor fully considers the relationships among body joints and produces more plausible pose predictions. With the guidance of predicted poses, a temporal discriminator encodes temporal information into future frame generation to achieve high-quality results. Furthermore, stacked residual refinement generators make the results more realistic. Extensive experiments on benchmark datasets demonstrate that the proposed method produces better predictions than state-ofthe- arts and achieves up to 15% improvement in PSNR.

23 October 2020 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
YZYang Zhao
Yang Zhao
YDYong Dou
Yong Dou
JFJiashi Feng
Jiashi Feng
This work addresses a challenging problem of estimating the full 3D human shape and pose from monocular videos. Since real-world 3D mesh-labeled datasets are limited, most current methods in 3D human shape reconstruction only focus on single RGB images, losing all the temporal information. In contrast, we propose temporally refined Graph U-Nets, including an image-level module and a video-level module, to solve this problem. The image-level module is Graph U-Nets for human shape and pose estimation from images, where the Graph Convolutional Neural Network (Graph CNN) helps the information communication of neighboring vertices, and the U-Nets architecture enlarges the receptive field of each vertex and fuses high-level and low-level features. The video-level module is a small Residual Temporal Graph CNN (Residual TG-CNN), which learns temporal dynamics from both structural and temporal neighbors. The temporal dynamics of each vertex are continuous in the temporal dimension and highly relevant to the structural neighbors, so it is helpful to diminish the ambiguity of the body in single images by fusing temporal dynamics. Our algorithm makes full use of labels from image-level datasets and refines the image-level results through video-level module. Evaluated on Human 3.6M and 3DPW datasets, our model produces accurate 3D human meshes and achieves superior 3D human pose estimation accuracy when compared with state-of-the-art methods.

5 February 2015 in IEEE Internet Computing
Verified
Journal Article
Closed access
EIElias Ioup
Elias Ioup
ZYZhao Yang
Zhao Yang
BBBrent Barré
Brent Barré
JSJohn Sample
John Sample
KSKevin B. Shaw
Kevin B. Shaw
MAMahdi Abdelguerfi
Mahdi Abdelguerfi
The Geography Markup Language (GML) - the existing standard for encoding geospatial data - has no mechanism for annotating such data with uncertainty. To address this issue while supporting the geospatial community's existing data and service standards, the authors extend GML to enable uncertainty markup. They demonstrate this extension's use with some common geospatial data types and Web services. The result is a robust capability to share error information while maintaining compatibility with existing geospatial data clients.