Xiaozhao Fang

Xiaozhao Fang

Auto-generated profile, based on publicly available information

Xiaozhao Fang

School of Automation, Guangdong University of Technology, Guangzhou, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
29 January 2018 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
Jie WenJie Wen
Jie Wen
XFXiaozhao Fang
Xiaozhao Fang
JCJinrong Cui
Jinrong Cui
LFLunke Fei
Lunke Fei
KYKe Yan
Ke Yan
YXYong Xu
Yong Xu
Linear discriminant analysis (LDA) is a very popular supervised feature extraction method and has been extended to different variants. However, classical LDA has the following problems: 1) The obtained discriminant projection does not have good interpretability for features. 2) LDA is sensitive to noise. 3) LDA is sensitive to the selection of number of projection directions. In this paper, a novel feature extraction method called robust sparse linear discriminant analysis (RSLDA) is proposed to solve the above problems. Specifically, RSLDA adaptively selects the most discriminative features for discriminant analysis by introducing the l2;1 norm. An orthogonal matrix and a sparse matrix are also simultaneously introduced to guarantee that the extracted features can hold the main energy of the original data and enhance the robustness to noise, and thus RSLDA has the potential to perform better than other discriminant methods. Extensive experiments on six databases demonstrate that the proposed method achieves the competitive performance compared with other state-of-the-art feature extraction methods. Moreover, the proposed method is robust to the noisy data.

15 February 2018 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
Jie WenJie Wen
Jie Wen
NHNa Han
Na Han
XFXiaozhao Fang
Xiaozhao Fang
LFLunke Fei
Lunke Fei
KYKe Yan
Ke Yan
SZShanhua Zhan
Shanhua Zhan
Preserving global and local structures during projection learning is very important for feature extraction. Although various methods have been proposed for this goal, they commonly introduce an extra graph regularization term and the corresponding regularization parameter that needs to be tuned. However, tuning the parameter manually not only is time-consuming, but also is difficult to find the optimal value to obtain a satisfactory performance. This greatly limits their applications. Besides, projections learned by many methods do not have good interpretability and their performances are commonly sensitive to the value of the selected feature dimension. To solve the above problems, a novel method named low-rank preserving projection via graph regularized reconstruction (LRPP_GRR) is proposed. In particular, LRPP_GRR imposes the graph constraint on the reconstruction error of data instead of introducing the extra regularization term to capture the local structure of data, which can greatly reduce the complexity of the model. Meanwhile, a low-rank reconstruction term is exploited to preserve the global structure of data. To improve the interpretability of the learned projection, a sparse term with l2,1 norm is imposed on the projection. Furthermore, we introduce an orthogonal reconstruction constraint to make the learned projection hold main energy of data, which enables LRPP_GRR to be more flexible in the selection of feature dimension. Extensive experimental results show the proposed method can obtain competitive performance with other state-of-the-art methods.

1 December 2018 in Neural Networks
Verified
Journal Article
Closed access
Jie WenJie Wen
Jie Wen
XFXiaozhao Fang
Xiaozhao Fang
YXYong Xu
Yong Xu
CTChunwei Tian
Chunwei Tian
LFLunke Fei
Lunke Fei

12 February 2018 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
XFXiaozhao Fang
Xiaozhao Fang
NHNa Han
Na Han
JWJigang Wu
Jigang Wu
YXYong Xu
Yong Xu
JYJian Yang
Jian Yang
XLXuelong Li
Xuelong Li
Feature extraction plays a significant role in pattern recognition. Recently, many representation-based feature extraction methods have been proposed and achieved successes in many applications. As an excellent unsupervised feature extraction method, latent low-rank representation (LatLRR) has shown its power in extracting salient features. However, LatLRR has the following three disadvantages: 1) the dimension of features obtained using LatLRR cannot be reduced, which is not preferred in feature extraction; 2) two low-rank matrices are separately learned so that the overall optimality may not be guaranteed; and 3) LatLRR is an unsupervised method, which by far has not been extended to the supervised scenario. To this end, in this paper, we first propose to use two different matrices to approximate the low-rank projection in LatLRR so that the dimension of obtained features can be reduced, which is more flexible than original LatLRR. Then, we treat the two low-rank matrices in LatLRR as a whole in the process of learning. In this way, they can be boosted mutually so that the obtained projection can extract more discriminative features. Finally, we extend LatLRR to the supervised scenario by integrating feature extraction with the ridge regression. Thus, the process of feature extraction is closely related to the classification so that the extracted features are discriminative. Extensive experiments are conducted on different databases for unsupervised and supervised feature extraction, and very encouraging results are achieved in comparison with many state-of-the-arts methods.

8 January 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
JLJiaxing Li
Jiaxing Li
WWWai Keung Wong
Wai Keung Wong
LJLin Jiang
Lin Jiang
XFXiaozhao Fang
Xiaozhao Fang
SXShengli Xie
Shengli Xie
YXYong Xu
Yong Xu
Recently, deep hashing-based cross-modal retrieval has attracted much attention of researchers, due to its advantages of fast retrieval efficiency and low storage overhead, etc. However, the existing deep hashing-based cross-modal retrieval methods typically 1) suffer from inadequately capturing the semantic relevance and coexistent information for cross-modal data, which may result in sub-optimal retrieval performance, 2) require a more comprehensive similarity measurement for cross-modal features to ensure high retrieval accuracy, 3) lack of scalability for lightweight deployment framework. To handle the issues mentioned above, we propose a CLIP-based knowledge distillation hashing (CKDH) for cross-modal retrieval, by referring the research trend of combining traditional methods and modern neural architecture to design lightweight networks based on large language models. Specifically, to effectively help capture the semantic relevance and coexistent information, CLIP is fine-tuned to extract visual features, while a graph attention network is used to enhance textual features extracted by bag-of-words model in the teacher model. Then, for better supervising the training of student model, a more comprehensive similarity measurement is introduced to represent distilled knowledge by jointly preserving the log-likelihood, intra and inter modality similarities. Finally, the student model extracts deep features by a lightweight networks, and generates the hash codes under the supervision of the similarity matrix produced by the teacher model. Experimental results on three widely used datasets demonstrate that CKDH can outperform some state-of-the-art methods, by delivering the best result consistently.

22 February 2019 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZPZhihao Peng
Zhihao Peng
WZWei Zhang
Wei Zhang
NHNa Han
Na Han
XFXiaozhao Fang
Xiaozhao Fang
PKPeipei Kang
Peipei Kang
LTLuyao Teng
Luyao Teng
Amajor assumption in data mining and machine learning is that the training set and test set come from the same domain.Theysharethe samefeature spaceandhavethe same distribution.However,in manyreal-world applications,the training set and test set usually come from different domains. Thus, there might be negative similarities between different domainsso thatthe negative transferproblem causedbynegative similaritymayhappen.In this paper, weproposeanovel method named active transfer learning (ATL) to solve the above problem. Speci?cally, the orthogonal projection matrix and theweight coef?cient vectorareintroducedtoextendmaximum mean discrepancy(MMD)sothatitcan minimizeMMDand simultaneouslyeliminate the negative transfer.To ?nd the informative and discriminative subsets from the source domain, we thenpropose an information diversity termbyusing the localgeometric structure informationof source samples. Besides,byusing the label information of source samples, our method can guarantee the selected subsets as discriminative as possible. Finally, to ef?cientlyimplement the proposed method, an alternating optimization approach, whichis based on the alternating direction methodofmultipliers (ADMM),is designedto solvethe optimizationproblem.To demonstratethe effectivenessoftheproposedATL model,theexperiments are conductedon ?ve real-world data sets.Theexperimental results show the superiority of our method over the state-of-the-art methods.