.png){kind=icon}
返回
Prototype Comparison Convolutional Networks for One-Shot Segmentation
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3387742.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In few-shot semantic segmentation (FSS), the key challenges are efficiently tuning the interaction between the support set and the query set and distinguishing between context, background, and interfering items. To address these challenges, we propose prototype comparison networks for one-shot segmentation (OPCN) to capture the details required for FSS. Specifically, we offer the Fusion Interaction Module (FIM) to improve the segmentation performance by capturing the correlation and semantic information between the support set and query set features. Subsequently, we propose the Feature Enhancement Module (FEM), which aims to enhance the information required in the support set and query set features while increasing the focus on critical details by reducing the weight of the background regions to provide a more targeted feature representation for subsequent query image segmentation. Then, we propose the Feature Refinement Module (FRM) to filter irrelevant background information in the features and specify the target location region. Finally, the Feature Matching Module (FM) generates the final segmentation mask for the query image. Extensive experiments on the PASCAL-5i and COCO-20i datasets show that our approach achieves excellent performance in the case of the one-shot setup.
Keyword:
Few-shot semantic segmentation
convolutional neural network
prototype network
feature matching
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Modeling Wood Fibre Length in Black Spruce (Picea mariana (Mill.) BSP) Based on Ecological Land Classification.png)
Forests
OAAI
ForestsIF0
OAAI分享收藏Torsional dynamics of molecules on barrierless potentials in liquids. II. Test of theoretical models
PREAI
分享收藏Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THVRSC Advances
RSC AdvancesIF0
PREAI
分享收藏分享收藏Few-shot defect recognition for the multi-domain industry via attention embedding and fine-grained feature enhancement通过注意力嵌入和细粒度特征增强的多领域行业少镜头缺陷识别
PREAI
分享收藏
查看更多内容