基于改进拆分注意力网络的目标检测算法  

Object Detection Algorithm Based on Improved Split-attention Network

作　　者：潘毅 王丽萍 PAN Yi;WANG Li-ping(College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China)

机构地区：[1]浙江工业大学计算机科学与技术学院,杭州310023

出　　处：《计算机科学》2022年第10期198-206,共9页Computer Science

基　　金：浙江省重点研发计划(2018C01080)。

摘　　要：当前,以卷积神经网络为基础的目标检测算法大多存在缺少对有价值的上下文信息的合理利用以及易对困难目标漏检等问题。针对这些问题,提出了一种基于改进拆分注意力网络的目标检测算法。首先,引入拆分注意力机制,将多通道结构与注意力机制相结合,提升其特征表示。然后,在网络的卷积层中使用多尺度卷积取代传统的卷积操作,增强了神经网络对尺度变化的敏感性。最后,将改进的网络应用于Faster R-CNN中,并在Pascal VOC数据集和MS COCO数据集上进行实验。所提算法在不增加超参数量及计算复杂度的情况下,其mAP相较于原始算法分别提升了1.6%和2.4%,且对比其他算法也有所优势,验证了所提算法的良好性能。Recently, most object detection algorithms based on convolutional neural network have the problems of lacking of reasonable use of meaningful contextual information and are easy to miss the detection of hard targets.In order to solve these problems, this paper proposes an object detection algorithm based on improved split-attention networks.Firstly, the split attention mechanism is introduced, and the multi-path structure is combined with feature-map attention mechanism to improve its feature representations.Then, in the convolution layer, poly-scale convolution is used to replace the vanilla convolution to enhance the scale-sensitivity of the neural network.Finally, the proposed algorithm is applied to Faster R-CNN.Experiments are carried out on Pascal VOC and MS COCO datasets.Compared with the original algorithm, the mAP of the proposed algorithm has improved 1.6% and 2.4% respectively without introducing additional parameters and computational complexities, and the mAP of the proposed algorithm is also higher than that of other algorithms, which verifies its good performance.

关 键 词：卷积神经网络 上下文信息 目标检测 拆分注意力 多尺度卷积 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]