目标检测
人工智能
计算机视觉
计算机科学
背景(考古学)
水下
特征(语言学)
棱锥(几何)
集合(抽象数据类型)
对象(语法)
特征提取
比例(比率)
人工神经网络
对象类检测
代表(政治)
模式识别(心理学)
数据集
特征检测(计算机视觉)
建筑
视觉对象识别的认知神经科学
噪音(视频)
噪声测量
网络体系结构
作者
Miao Yang,Jinyang Zhong,H. Zhang,Can Pan,Xinmiao Gao,Chenglong Gong
标识
DOI:10.1109/joe.2024.3450532
摘要
Underwater object detection (UOD) is more difficult than object detection in air due to the noise caused by irrelevant objects and textures, and the scale variation. These difficulties pose a higher challenge to the feature extraction capability of detectors. Feature pyramid network (FPN) enhances the scale detection capability of detectors, while attention mechanisms effectively suppress irrelevant features. We present a cross-scale attention feature pyramid network (CSAFPN) for UOD. A feature fusion guided (FFG) module is incorporated in the CSAFPN, which constructs cross-scale context information and simultaneously guides the enhancement of all feature maps. Compared to existing FPN-like architectures, CSAFPN excels not only in capturing cross-scale long-range dependencies but also in acquiring compact multi-scale feature maps that specifically emphasize target regions. Extensive experiments on the Brackish2019 data set show that CSAFPN can achieve consistent improvements on various backbones and detectors. Moreover, FFG can be seamlessly integrated into any FPN-like architecture, offering a cost-effective improvement in UOD, resulting in a 1.4% average precision (AP) increase for FPN, a 1.3% AP increase for PANet, and a 1.4% AP increase for neural architecture search-FPN.
科研通智能强力驱动
Strongly Powered by AbleSci AI