Siyan Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Siyan Sun has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Hong Peng
School of Computer and Software Engineering, Xihua University, Chengdu 610039, P. R. China
2 shared publications - Zhicai Liu
Xihua University
2 shared publications - Jun Wang
School of Electrical Engineering and Electronic Information, Xihua University, Chengdu, China
1 shared publication - Peng Wang
School of Computer and Software Engineering, Xihua University, Chengdu 610039, P. R. China
1 shared publication - Zhengyuan Jiang
School of Computer and Software Engineering, Xihua University, Chengdu 610039, P. R. China
1 shared publication
Latest Publications
- 23 September 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 34 (12) , 2450064
Referring Image Segmentation with Multi-Modal Feature Interaction and Alignment Based on Convolutional Nonlinear Spiking Neural Membrane Systems
Referring image segmentation aims to accurately align image pixels and text features for object segmentation based on natural language descriptions. This paper proposes NSNPRIS (convolutional nonlinear spiking neural P systems for referring image segmentation), a novel model based on convolutional nonlinear spiking neural P systems. NSNPRIS features NSNPFusion and Language Gate modules to enhance feature interaction during encoding, along with an NSNPDecoder for feature alignment and decoding. Experimental results on RefCOCO, RefCOCO[ ], and G-Ref datasets demonstrate that NSNPRIS performs better than mainstream methods. Our contributions include advances in the alignment of pixel and textual features and the improvement of segmentation accuracy.
- 23 September 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 34 (12) , 2450064
Referring Image Segmentation with Multi-Modal Feature Interaction and Alignment Based on Convolutional Nonlinear Spiking Neural Membrane Systems
Referring image segmentation aims to accurately align image pixels and text features for object segmentation based on natural language descriptions. This paper proposes NSNPRIS (convolutional nonlinear spiking neural P systems for referring image segmentation), a novel model based on convolutional nonlinear spiking neural P systems. NSNPRIS features NSNPFusion and Language Gate modules to enhance feature interaction during encoding, along with an NSNPDecoder for feature alignment and decoding. Experimental results on RefCOCO, RefCOCO[ ], and G-Ref datasets demonstrate that NSNPRIS performs better than mainstream methods. Our contributions include advances in the alignment of pixel and textual features and the improvement of segmentation accuracy.
- 13 April 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 34 (07) , 2450035
Multiple-in-Single-Out Object Detector Leveraging Spiking Neural Membrane Systems and Multiple Transformers
Most existing multi-scale object detectors depend on multi-level feature maps. The Feature Pyramid Networks (FPN) is a significant architecture for object detection that utilizes these multi-level feature maps. However, the use of FPN also increases the detector’s complexity. For object detection methods that only use a single-level feature map, the detection performance is limited to some extent because the single-level feature map cannot balance deep semantic information and shallow detail information. We introduce a novel detector — the Spiking Neural P Multiple-in-Single-out (SNPMiSo) detector to address these challenges. The SNPMiSo detector is constructed based on SNP-like neurons. In SNPMiSo, we employ two kinds of Transformers to boost the important features across different-level feature maps separately. After enhancing the features, we use an incremental upsampling module to upsample and merge the two feature maps. This combined feature map is input into the NAF dilated residual module and the NAF dual-branch detection head. This process allows us to extract multi-scale features and carry out detection tasks. Our tests show promising results: On the COCO dataset, SNPMiSo attains an Average Precision (AP) of 38.7, an improvement of 1.0 AP over YOLOF. In addition, SNPMiSo demonstrates a quicker detection speed, outperforming some advanced multi-level and single-level object detectors.
- 13 April 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Neural Systems
- Vol. 34 (07) , 2450035
Multiple-in-Single-Out Object Detector Leveraging Spiking Neural Membrane Systems and Multiple Transformers
Most existing multi-scale object detectors depend on multi-level feature maps. The Feature Pyramid Networks (FPN) is a significant architecture for object detection that utilizes these multi-level feature maps. However, the use of FPN also increases the detector’s complexity. For object detection methods that only use a single-level feature map, the detection performance is limited to some extent because the single-level feature map cannot balance deep semantic information and shallow detail information. We introduce a novel detector — the Spiking Neural P Multiple-in-Single-out (SNPMiSo) detector to address these challenges. The SNPMiSo detector is constructed based on SNP-like neurons. In SNPMiSo, we employ two kinds of Transformers to boost the important features across different-level feature maps separately. After enhancing the features, we use an incremental upsampling module to upsample and merge the two feature maps. This combined feature map is input into the NAF dilated residual module and the NAF dual-branch detection head. This process allows us to extract multi-scale features and carry out detection tasks. Our tests show promising results: On the COCO dataset, SNPMiSo attains an Average Precision (AP) of 38.7, an improvement of 1.0 AP over YOLOF. In addition, SNPMiSo demonstrates a quicker detection speed, outperforming some advanced multi-level and single-level object detectors.