Jialin Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jialin Tang has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Binghua Su
Beijing Institute of Technology, Zhuhai 519088, China
3 shared publications - Yongqi Tian
Beijing Institute of Technology
3 shared publications - Xiaoxiang Liu
School of Intelligent Systems Science and Engineering Jinan University Guangdong China
2 shared publications - Xinyuan Zhang
School of Intelligent Systems Science and Engineering Jinan University Zhuhai China
2 shared publications - Xueyuan Gong
School of Intelligent Systems Science and Engineering, Jinan University, Zhuhai, China
2 shared publications Benxi Yang
Key Laboratory of Intelligent Detection in Complex Environment of Aerospace Land and Sea, Beijing Institute of Technology, Zhuhai, China
1 shared publication
Latest Publications
- 22 December 2024
- Published by Springer Nature
- p. 165-176
Defect Detection Based on Normalized Attention Mechanism and Multi-level Feature Fusion
- 22 December 2024
- Published by Springer Nature
- p. 165-176
Defect Detection Based on Normalized Attention Mechanism and Multi-level Feature Fusion
- 18 February 2023
- Published by Springer Nature
- p. 139-148
Effects of Different Normalization on the ESRGAN
- 18 February 2023
- Published by Springer Nature
- p. 139-148
Effects of Different Normalization on the ESRGAN
- Open Access
- 29 November 2022
- Published by Frontiers Media SA in Frontiers in Marine Science
- Vol. 9
RMP-Net: A structural reparameterization and subpixel super-resolution-based marine scene segmentation network
Ocean exploration has always been an important strategic direction for the joint efforts of all mankind. Many countries in the world today are developing their own underwater autonomous explorers to better explore the seabed. Vision, as the core technology of autonomous underwater explorers, has a great impact on the efficiency of exploration. Different from traditional tasks, the lack of ambient light on the seabed makes the visual system more demanding. In addition, the complex terrain on the seabed and various creatures with different shapes and colors also make exploration tasks more difficult. In order to effectively solve the above problems, we combined the traditional models to modify the structure and proposed an algorithm for the super-resolution fusion of enhanced extraction features to perform semantic segmentation of seabed scenes. By using a structurally reparameterized backbone network to better extract target features in complex environments, and using subpixel super-resolution to combine multiscale feature semantic information, we can achieve superior ocean scene segmentation performance. In this study, multiclass segmentation and two-class segmentation tests were performed on the public datasets SUIM and DeepFish, respectively. The test results show that the mIoU and mPA indicators of our proposed method on SUIM reach 84.52% and 92.33%mPA, respectively. The mIoU and mPA on DeepFish reach 95.26% and 97.38%, respectively, and the proposed model achieves SOTA compared with state-of-the-art methods. The proposed model and code are exposed via Github 1 .
- 29 November 2022
- Published by Frontiers Media SA in Frontiers in Marine Science
- Vol. 9
Open AccessRMP-Net: A structural reparameterization and subpixel super-resolution-based marine scene segmentation network
Ocean exploration has always been an important strategic direction for the joint efforts of all mankind. Many countries in the world today are developing their own underwater autonomous explorers to better explore the seabed. Vision, as the core technology of autonomous underwater explorers, has a great impact on the efficiency of exploration. Different from traditional tasks, the lack of ambient light on the seabed makes the visual system more demanding. In addition, the complex terrain on the seabed and various creatures with different shapes and colors also make exploration tasks more difficult. In order to effectively solve the above problems, we combined the traditional models to modify the structure and proposed an algorithm for the super-resolution fusion of enhanced extraction features to perform semantic segmentation of seabed scenes. By using a structurally reparameterized backbone network to better extract target features in complex environments, and using subpixel super-resolution to combine multiscale feature semantic information, we can achieve superior ocean scene segmentation performance. In this study, multiclass segmentation and two-class segmentation tests were performed on the public datasets SUIM and DeepFish, respectively. The test results show that the mIoU and mPA indicators of our proposed method on SUIM reach 84.52% and 92.33%mPA, respectively. The mIoU and mPA on DeepFish reach 95.26% and 97.38%, respectively, and the proposed model achieves SOTA compared with state-of-the-art methods. The proposed model and code are exposed via Github 1 .
- 22 July 2022
- Published by Springer Nature
- p. 267-276
A MobileNet SSDLite Model with Improved FPN for Forest Fire Detection
- 22 July 2022
- Published by Springer Nature
- p. 267-276
A MobileNet SSDLite Model with Improved FPN for Forest Fire Detection
- 21 May 2022
- Published by Elsevier in Neural Networks
- Vol. 152, 487-498
GIU-GANs: Global Information Utilization for Generative Adversarial Networks
- 21 May 2022
- Published by Elsevier in Neural Networks
- Vol. 152, 487-498
GIU-GANs: Global Information Utilization for Generative Adversarial Networks
- Open Access
GIU-GANs: Global Information Utilization for Generative Adversarial Networks
In recent years, with the rapid development of artificial intelligence, image generation based on deep learning has dramatically advanced. Image generation based on Generative Adversarial Networks (GANs) is a promising study. However, since convolutions are limited by spatial-agnostic and channel-specific, features extracted by traditional GANs based on convolution are constrained. Therefore, GANs are unable to capture any more details per image. On the other hand, straightforwardly stacking of convolutions causes too many parameters and layers in GANs, which will lead to a high risk of overfitting. To overcome the aforementioned limitations, in this paper, we propose a new GANs called Involution Generative Adversarial Networks (GIU-GANs). GIU-GANs leverages a brand new module called the Global Information Utilization (GIU) module, which integrates Squeeze-and-Excitation Networks (SENet) and involution to focus on global information by channel attention mechanism, leading to a higher quality of generated images. Meanwhile, Batch Normalization(BN) inevitably ignores the representation differences among noise sampled by the generator, and thus degrade the generated image quality. Thus we introduce Representative Batch Normalization(RBN) to the GANs architecture for this issue. The CIFAR-10 and CelebA datasets are employed to demonstrate the effectiveness of our proposed model. A large number of experiments prove that our model achieves state-of-the-art competitive performance.
Open AccessGIU-GANs: Global Information Utilization for Generative Adversarial Networks
In recent years, with the rapid development of artificial intelligence, image generation based on deep learning has dramatically advanced. Image generation based on Generative Adversarial Networks (GANs) is a promising study. However, since convolutions are limited by spatial-agnostic and channel-specific, features extracted by traditional GANs based on convolution are constrained. Therefore, GANs are unable to capture any more details per image. On the other hand, straightforwardly stacking of convolutions causes too many parameters and layers in GANs, which will lead to a high risk of overfitting. To overcome the aforementioned limitations, in this paper, we propose a new GANs called Involution Generative Adversarial Networks (GIU-GANs). GIU-GANs leverages a brand new module called the Global Information Utilization (GIU) module, which integrates Squeeze-and-Excitation Networks (SENet) and involution to focus on global information by channel attention mechanism, leading to a higher quality of generated images. Meanwhile, Batch Normalization(BN) inevitably ignores the representation differences among noise sampled by the generator, and thus degrade the generated image quality. Thus we introduce Representative Batch Normalization(RBN) to the GANs architecture for this issue. The CIFAR-10 and CelebA datasets are employed to demonstrate the effectiveness of our proposed model. A large number of experiments prove that our model achieves state-of-the-art competitive performance.