Yongbin Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yongbin Zhu has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
Bixue Guo
3 shared publications- Yunyun Yang
Harbin Institute of Technology
3 shared publications Zilong Yu
3 shared publications- Chun Li
Shenzhen MSU-BIT University
1 shared publication - Chunyi Zhi
The University of Hong Kong
1 shared publication - Feng Jiang
Institute of Flexible Electronics Technology of Tsinghua Jiaxing Zhejiang 314000 China
1 shared publication
Latest Publications
- 24 October 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Domain divergence minimization for unsupervised domain adaptation cross-modality medical image segmentation
- 24 October 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Domain divergence minimization for unsupervised domain adaptation cross-modality medical image segmentation
- 24 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 283
Multi-modality medical image segmentation via adversarial learning with CV energy functional
- 24 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 283
Multi-modality medical image segmentation via adversarial learning with CV energy functional
- 20 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 663-672
CS-IntroVAE: Cauchy-Schwarz Divergence-Based Introspective Variational Autoencoder
Although generative models are still being developed, image reconstruction and generation tasks have evolved dramatically. Since the most popular generative models still have some limitations, it is still challenging. For example, while generative adversarial network (GAN) produces clear images, it is hard to train. The hybrid VAE-GAN incorporates the benefits of both, although it is computationally intensive and prone to drawbacks such as overfitting and gradient disappearance. A novel generative model called the Cauchy-Schwarz Divergence-based Introspective Variational Autoencoder (CS-IntroVAE) is based for this challenge. Extensive experiments show that our model has good performance on both tasks by employing mixed Gaussian distributions as prior distributions and Cauchy-Schwarz divergence as a measure of the distance between prior and posterior distributions. The source code is available at https://github.com/CoderSnack/CS-IntroVAE .
- 20 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 663-672
CS-IntroVAE: Cauchy-Schwarz Divergence-Based Introspective Variational Autoencoder
Although generative models are still being developed, image reconstruction and generation tasks have evolved dramatically. Since the most popular generative models still have some limitations, it is still challenging. For example, while generative adversarial network (GAN) produces clear images, it is hard to train. The hybrid VAE-GAN incorporates the benefits of both, although it is computationally intensive and prone to drawbacks such as overfitting and gradient disappearance. A novel generative model called the Cauchy-Schwarz Divergence-based Introspective Variational Autoencoder (CS-IntroVAE) is based for this challenge. Extensive experiments show that our model has good performance on both tasks by employing mixed Gaussian distributions as prior distributions and Cauchy-Schwarz divergence as a measure of the distance between prior and posterior distributions. The source code is available at https://github.com/CoderSnack/CS-IntroVAE .
- 15 October 2021
- Published by Wiley in Angewandte Chemie
- Vol. 134 (2)
Vacancy Modulating Co3Sn2S2 Topological Semimetal for Aqueous Zinc‐Ion Batteries
Weyl semimetals (WSMs) with high electrical conductivity and suitable carrier density near the Fermi level are enticing candidates for aqueous Zn‐ion batteries (AZIBs), meriting from topological surface states (TSSs). We propose a WSM Co3Sn2S2 cathode for AZIBs showing a discharge plateau around 1.5 V. By introducing Sn vacancies, extra redox peaks from the Sn4+/Sn2+ transition appear, which leads to more Zn2+ transfer channels and active sites promoting charge‐storage kinetics and Zn2+ storage capability. Co3Sn1.8S2 achieves a specific energy of 305 Wh kg−1 (0.2 Ag−1) and a specific power of 4900 Wkg−1 (5 Ag−1). Co3Sn1.8S2 and ZnxCo3Sn1.8S2 benefit from better conductivity at lower temperatures; the quasi‐solid Co3Sn1.8S2//Zn battery delivers 126 mAh g−1 (0.6 Ag−1) at −30 °C and a cycling stability over 3000 cycles (2 Ag−1) with 85 % capacity retention at −10 °C.
- 15 October 2021
- Published by Wiley in Angewandte Chemie
- Vol. 134 (2)
Vacancy Modulating Co3Sn2S2 Topological Semimetal for Aqueous Zinc‐Ion Batteries
Weyl semimetals (WSMs) with high electrical conductivity and suitable carrier density near the Fermi level are enticing candidates for aqueous Zn‐ion batteries (AZIBs), meriting from topological surface states (TSSs). We propose a WSM Co3Sn2S2 cathode for AZIBs showing a discharge plateau around 1.5 V. By introducing Sn vacancies, extra redox peaks from the Sn4+/Sn2+ transition appear, which leads to more Zn2+ transfer channels and active sites promoting charge‐storage kinetics and Zn2+ storage capability. Co3Sn1.8S2 achieves a specific energy of 305 Wh kg−1 (0.2 Ag−1) and a specific power of 4900 Wkg−1 (5 Ag−1). Co3Sn1.8S2 and ZnxCo3Sn1.8S2 benefit from better conductivity at lower temperatures; the quasi‐solid Co3Sn1.8S2//Zn battery delivers 126 mAh g−1 (0.6 Ag−1) at −30 °C and a cycling stability over 3000 cycles (2 Ag−1) with 85 % capacity retention at −10 °C.