Xiaojing Zhang
Xiaojing Zhang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Bo Yang
Shandong Key Laboratory of Ubiquitous Intelligent Computing, University of Jinan, Jinan, China
1 shared publication Cuiping Tan
Institute of Information on Science and Technology of Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing, 100097, China
1 shared publicationHaruto Tanno
NTT Cyber Space Laboratories, Nippon Telegraph and Telephone Corporation, Yokosuka, Japan
1 shared publicationHuaiguo Zheng
Institute of Information on Science and Technology of Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing, 100097, China
1 shared publication- Lin Wang
Monash-Airdoc joint research group, Monash University, Melbourne, VIC, Australia
1 shared publication - Takashi Hoshino
Cybozu Labs, Inc., Tokyo, Japan
1 shared publication
Latest Publications
- 18 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Learning Effective Discriminative Features with Differentiable Magnet Loss
Neural network optimization relies on the ability of the loss function to learn highly discriminative features. In recent years, Softmax loss has been widely used to train neural network models in various tasks. In order to further enhance the discriminative power of the learned features, Center loss is introduced as an auxiliary function to aid Softmax loss jointly reduce the intra-class variances. In this paper, we propose a novel loss called Differentiable Magnet loss (DML), which can optimize neural nets independently of Softmax loss without joint supervision. This loss offers a more definite convergence target for each class, which not only allows the sample to be close to the homogeneous (intra-class) center but also to stay away from all heterogeneous (inter-class) centers in the feature embedding space. Extensive experimental results demonstrate the superiority of DML in a variety of classification and clustering tasks. Specifically, the 2-D visualization of the learned embedding features by t-SNE effectively proves that our proposed new loss can learn better discriminative representations.
- 18 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Learning Effective Discriminative Features with Differentiable Magnet Loss
Neural network optimization relies on the ability of the loss function to learn highly discriminative features. In recent years, Softmax loss has been widely used to train neural network models in various tasks. In order to further enhance the discriminative power of the learned features, Center loss is introduced as an auxiliary function to aid Softmax loss jointly reduce the intra-class variances. In this paper, we propose a novel loss called Differentiable Magnet loss (DML), which can optimize neural nets independently of Softmax loss without joint supervision. This loss offers a more definite convergence target for each class, which not only allows the sample to be close to the homogeneous (intra-class) center but also to stay away from all heterogeneous (inter-class) centers in the feature embedding space. Extensive experimental results demonstrate the superiority of DML in a variety of classification and clustering tasks. Specifically, the 2-D visualization of the learned embedding features by t-SNE effectively proves that our proposed new loss can learn better discriminative representations.
- 12 January 2021
- Published by Springer Nature in Journal of Systems Science and Complexity
- Vol. 34 (6) , 2378-2395
A Strongly-Consistent Difference Scheme for 3D Nonlinear Navier-Stokes Equations
- 12 January 2021
- Published by Springer Nature in Journal of Systems Science and Complexity
- Vol. 34 (6) , 2378-2395
A Strongly-Consistent Difference Scheme for 3D Nonlinear Navier-Stokes Equations
- Open Access
Algebraic Construction of a Strongly Consistent, Permutationally Symmetric and Conservative Difference Scheme for 3D Steady Stokes Flow
By using symbolic algebraic computation, we construct a strongly-consistent second-order finite difference scheme for steady three-dimensional Stokes flow and a Cartesian solution grid. The scheme has the second order of accuracy and incorporates the pressure Poisson equation. This equation is the integrability condition for the discrete momentum and continuity equations. Our algebraic approach to the construction of difference schemes suggested by the second and the third authors combines the finite volume method, numerical integration, and difference elimination. We make use of the techniques of the differential and difference Janet/Gröbner bases for performing related computations. To prove the strong consistency of the generated scheme, we use these bases to correlate the differential ideal generated by the polynomials in the Stokes equations with the difference ideal generated by the polynomials in the constructed difference scheme. As this takes place, our difference scheme is conservative and inherits permutation symmetry of the differential Stokes flow. For the obtained scheme, we compute the modified differential system and use it to analyze the scheme’s accuracy.
Open AccessAlgebraic Construction of a Strongly Consistent, Permutationally Symmetric and Conservative Difference Scheme for 3D Steady Stokes Flow
By using symbolic algebraic computation, we construct a strongly-consistent second-order finite difference scheme for steady three-dimensional Stokes flow and a Cartesian solution grid. The scheme has the second order of accuracy and incorporates the pressure Poisson equation. This equation is the integrability condition for the discrete momentum and continuity equations. Our algebraic approach to the construction of difference schemes suggested by the second and the third authors combines the finite volume method, numerical integration, and difference elimination. We make use of the techniques of the differential and difference Janet/Gröbner bases for performing related computations. To prove the strong consistency of the generated scheme, we use these bases to correlate the differential ideal generated by the polynomials in the Stokes equations with the difference ideal generated by the polynomials in the constructed difference scheme. As this takes place, our difference scheme is conservative and inherits permutation symmetry of the differential Stokes flow. For the obtained scheme, we compute the modified differential system and use it to analyze the scheme’s accuracy.
- 1 September 2014
- Published by WITPRESS LTD.
- Vol. 2, 1217-1223
Research and practice on agricultural information resource integration and sharing services
Welcome to the WIT Press eLibrary - the home of the Transactions of the Wessex Institute collection, providing on-line access to papers presented at the Institute's prestigious international conferences and from its State-of-the-Art in Science & Engineering publications.
- 1 September 2014
- Published by WITPRESS LTD.
- Vol. 2, 1217-1223
Research and practice on agricultural information resource integration and sharing services
Welcome to the WIT Press eLibrary - the home of the Transactions of the Wessex Institute collection, providing on-line access to papers presented at the Institute's prestigious international conferences and from its State-of-the-Art in Science & Engineering publications.
- 1 March 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 559-560
Introducing Test Case Derivation Techniques into Traditional Software Development: Obstacles and Potentialities
In traditional development, extracting test cases manually is an effort-consuming and error-prone process. To examine whether automation techniques can be integrated into such traditional development, we implemented our previously proposed method to "TesMa", a test case generation tool. We had a case study to evaluate the effectiveness and the cost.
- 1 March 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 559-560
Introducing Test Case Derivation Techniques into Traditional Software Development: Obstacles and Potentialities
In traditional development, extracting test cases manually is an effort-consuming and error-prone process. To examine whether automation techniques can be integrated into such traditional development, we implemented our previously proposed method to "TesMa", a test case generation tool. We had a case study to evaluate the effectiveness and the cost.