.png){kind=icon}
返回
Neighbour feature attention-based pooling
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2022.05.094.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In modern convolutional neural networks (CNNs), the pooling layer is seen as one of the primary layers for building the CNN model, which effectively downscales the spatial size of feature maps to reduce memory consumption. Several types of pooling operations, such as average pooling, max pooling, and strided convolution, fail to capture the spatial dependence between the pooling region feature and its neighbour features. In this paper, we propose a simple but effective attention-based pooling method called Neighbour Feature Attention-Based Pooling (NFP), which integrates neighbour features of the pooling region to keep semantic continuity across multiple layers. NFP adopts attention weights encoding with neighbour features by depthwise convolution, which effectively directs local spatial pooling for learning discriminative features. Compared to other pooling methods, the proposed method generates more discriminative features directed by neighbour information of the pooling region. The experiments results show that it consistently improves the performance across various backbone architectures on image classification tasks.(c) 2022 Elsevier B.V. All rights reserved.
Keyword:
Convolutional neural network
Pooling method
Neighbour feature attention
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Exergoeconomic performance of an endoreversible Carnot heat pump with complex heat transfer law
PREAI
分享收藏Structural study of lanthanides(III) in aqueous nitrate and chloride solutions by EXAFS通过EXAFS对硝酸盐和氯化物水溶液中镧系元素 (III) 的结构研究
PREAI
分享收藏
The power of obfuscation techniques in malicious JavaScript code: A measurement study恶意JavaScript代码中混淆技术的功能: 一项测量研究
OAAI
OAAI分享收藏分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏
查看更多内容