CXChenjing Xin
Chenjing Xin
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Chenjing Xin has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Xinfu Li
School of Cyber Security and Computer, Hebei University, Baoding 071002, China
1 shared publication - Yunfeng Yuan
School of Cyber Security and Computer, Hebei University, Baoding 071002, China
1 shared publication
Latest Publications
- Open Access
- 5 October 2022
- Published by MDPI AG in Electronics
- Vol. 11 (19) , 3195
Multilevel Features-Guided Network for Few-Shot Segmentation
The purpose of few-shot semantic segmentation is to segment unseen classes with only a few labeled samples. However, most methods ignore the guidance of low-level features for segmentation, leading to unsatisfactory results. Therefore, we propose a multilevel features-guided network using convolutional neural network techniques, which fully utilizes features from each level. It includes two novel designs: (1) a similarity-guided feature reinforcement module (SRM), which uses features from different levels, it enables sufficient guidance from the support set to the query set, thus avoiding the situation that some feature information is ignored in deep network computation, (2) a method that bridges query features at each level to the decoder to guide the segmentation, making full use of local and edge information to improve model performance. We experiment on PASCAL-5 and COCO-20 datasets to demonstrate the effectiveness of the model, the results in 1-shot setting and 5-shot setting on PASCAL-5 are 64.7% and 68.0%, which are 3.9% and 6.1% higher than the baseline model, respectively, and the results on the COCO-20 are also improved.- 5 October 2022
- Published by MDPI AG in Electronics
- Vol. 11 (19) , 3195
Open AccessMultilevel Features-Guided Network for Few-Shot Segmentation
The purpose of few-shot semantic segmentation is to segment unseen classes with only a few labeled samples. However, most methods ignore the guidance of low-level features for segmentation, leading to unsatisfactory results. Therefore, we propose a multilevel features-guided network using convolutional neural network techniques, which fully utilizes features from each level. It includes two novel designs: (1) a similarity-guided feature reinforcement module (SRM), which uses features from different levels, it enables sufficient guidance from the support set to the query set, thus avoiding the situation that some feature information is ignored in deep network computation, (2) a method that bridges query features at each level to the decoder to guide the segmentation, making full use of local and edge information to improve model performance. We experiment on PASCAL-5 and COCO-20 datasets to demonstrate the effectiveness of the model, the results in 1-shot setting and 5-shot setting on PASCAL-5 are 64.7% and 68.0%, which are 3.9% and 6.1% higher than the baseline model, respectively, and the results on the COCO-20 are also improved.