基于深度可分离卷积和交叉注意力的水面污染识别
Water Surface Pollution Recognition Based on Deep-wise Convolution and Cross Attention
王宁 1杨志斌1
作者信息
- 1. 中国科学院沈阳计算技术研究所,沈阳 110168;中国科学院大学,北京 100049
- 折叠
摘要
水面污染严重影响水面景观和水体生态.针对识别水面污染过程中水面场景复杂、小目标污染物特征难以提取等问题,本文提出一种基于深度可分离卷积与交叉注意力算法模块(deep-wise convolution and cross attention,DCCA).使用深度可分离卷积降低模型的参数量和计算量,使用交叉注意力建立不同尺度特征图之间的关系,使模型更好地理解上下文信息并提高识别复杂场景和小目标的能力.实验结果表明,添加DCCA模块后平均精确率提升了 1.8％,达到了 88.7％.并使用较少的显存占用提高了水面污染的检测效果.
Abstract
Water pollution seriously affects the water landscape and water ecology.In this study,a deep-wise convolution and cross attention(DCCA)algorithm module is proposed to address the issues of complex water surface scenes and difficulty in extracting features of small target pollutants in the process of identifying water surface pollution.The use of deep-wise convolution reduces the parameters and computational complexity of the model,and establishes relationships between feature maps at different scales using cross attention,enabling the model to better understand contextual information and improve its ability to recognize complex scenes and small targets.The experimental results show that the average accuracy has been improved by 1.8％ after adding the DCCA module,reaching 88.7％.The detection effect of water surface pollution has been improved by using less memory occupation.
关键词
深度可分离卷积/交叉注意力/污染识别/目标检测/卷积神经网络/深度学习Key words
deep-wise convolution/cross attention/pollution recognition/object detection/convolutional neural network(CNN)/deep learning引用本文复制引用
基金项目
辽宁省应用基础研究计划(2022JH2/101300126)
沈阳市中青年科技创新人才支持计划(RC210360)
出版年
2024
NETL
NSTL
维普
万方数据