.png){kind=icon}
返回
Few-shot object segmentation with a new feature aggregation module
.png){kind=icon}
PRE
AI
DOI：10.1016/j.displa.2023.102459.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The success of convolutional neural network for object segmentation depends on a large amount of training data and high-quality samples. But annotating such high-quality training data for pixel-wise segmentation is labor-intensive. To reduce the massive labor work, few-shot learning has been introduced to segment objects, which uses a few samples for training without compromising the performance. However, the current few-shot models are biased towards the seen classes rather than being class-irrelevant due to lack of global context prior attention. Therefore, this study aims at proposing a few-shot object segmentation model with a new feature aggregation module. Specifically, the proposed work develops a detail-aware module to enhance the discrimination of details with diversified attributes. To enhance the semantics of each pixel, we propose a global attention module to aggregate detailed features containing semantic information. Furthermore, to improve the performance of the proposed model, the model uses support samples that represents class-specific prototype obtained by respective category prototype block. Next, the proposed model predicts label of each pixel of query sample by estimating the distance between the pixel and prototypes. Experiments on standard datasets demonstrate significance of the proposed model over SOTA in terms of segmentation with a few training samples.
Keyword:
Few-shot learning
Object segmentation
Feature aggregation
Attention mechanism
期刊
IF:
3.4
论文数:
2.3K
被引数:
3.2K
机构
引用论文
Evaluating environmental liability through risk premiums charged on loans to agribusiness borrowers.png)
Agribusiness
AgribusinessIF0
PREAI
分享收藏On the nature and permeability of chitin. I.--The chitin lining the foregut of decapod crustacea and the function of the tegumental glandsProceedings of the Royal Society of London. Series B, Containing Papers of a Biological Character
Proceedings of the Royal Society of London. Series B, Containing Papers of a Biological CharacterIF0
PREAI
分享收藏Recent Development of Dual-Dictionary Learning Approach in Medical Image Analysis and Reconstruction
OAAI
OAAI分享收藏Thermal comfort, perceived air quality, and cognitive performance when personally controlled air movement is used by tropically acclimatized persons当热带适应的人使用个人控制的空气运动时，热舒适性，感知的空气质量和认知表现Indoor AirOAAI
Indoor AirIF0
OAAI分享收藏
查看更多内容