Attention-Enhanced Lightweight One-Stage Detection Algorithm for Small Objects

作者
Nan Jia,Zongkang Wei,Bangyu Li
出处
期刊:Electronics [Multidisciplinary Digital Publishing Institute]
卷期号:12 (7): 1607-1607 被引量:8
标识
DOI:10.3390/electronics12071607
摘要

The majority of object detection algorithms based on convolutional neural network are focused on larger objects. In order to improve the accuracy and efficiency of small object detection, a novel lightweight object detection algorithm with attention enhancement is proposed in this paper. The network part of the proposed algorithm is based on a single-stage framework and takes MobileNetV3-Large as a backbone. The representation of shallower scale features in the scale fusion module is enhanced by introducing an additional injection path from the backbone and a detection head specially responsible for detecting small objects is added. Instead of pooling operators, dilated convolution with hierarchical aggregation is used to reduce the effect of background pixels on the accuracy of small object locations. To improve the efficacy of merging, the spatial and channel weights of scale features are modified adaptively. Last but not least, to improve the representation of small objects in the training datasets, the Consistent Mixed Cropping method is also proposed. The small labels of standard datasets are expanded with the self-collected samples for the training of the algorithm network. According to the test results and visualization on the 64-Bit Extended (X86-64) platform and embedded Advanced RISC Machine (ARM) platform, we find that the average accuracy (mAP) of the proposed algorithm is 4.6% higher than YOLOv4 algorithm, which achieves better small object detection performance than YOLOv4 algorithm, and the computational complexity is only 12% of YOLOv4 algorithm.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
酷波er的应助被科研通管家采纳,获得10
刚刚
打打的应助被科研通管家采纳,获得10
刚刚
刚刚
FashionBoy的应助被科研通管家采纳,获得10
刚刚
搜集达人的应助被科研通管家采纳,获得10
刚刚
斯文败类的应助被科研通管家采纳,获得10
刚刚
秋风的应助被科研通管家采纳,获得20
刚刚
刚刚
Owen的应助被科研通管家采纳,获得10
1秒前
秋风的应助被科研通管家采纳,获得10
1秒前
1秒前
1秒前
1秒前
1秒前
无极微光的应助被科研通管家采纳,获得20
1秒前
大模型的应助被科研通管家采纳,获得10
1秒前
共享精神的应助被科研通管家采纳,获得10
2秒前
无极微光的应助被科研通管家采纳,获得20
2秒前
上官若男的应助被科研通管家采纳,获得10
2秒前
大海的叹息完成签到 ,获得积分10
2秒前
2秒前
李健的应助被是小鱼采纳,获得10
2秒前
隐形曼青的应助被yuanyu采纳,获得10
2秒前
研友_VZG7GZ的应助被科研通管家采纳,获得10
2秒前
3秒前
苏黎世完成签到,获得积分10
3秒前
小棕瓶完成签到,获得积分10
3秒前
Wenlia的应助被旧巷听风采纳,获得10
4秒前
桐桐的应助被ok采纳,获得30
4秒前
orixero的应助被七安采纳,获得10
5秒前
xyz发布了新的文献求助100
5秒前
Rachel完成签到 ,获得积分10
5秒前
大模型的应助被荼蘼采纳,获得10
6秒前
情怀的应助被荼蘼采纳,获得10
6秒前
吹圆号的小熊猫的应助被荼蘼采纳,获得30
6秒前
奔跑的应助被荼蘼采纳,获得200
6秒前
奔跑的应助被荼蘼采纳,获得10
7秒前
7秒前
Nexus的应助被荼蘼采纳,获得50
7秒前
烟花的应助被荼蘼采纳,获得10
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
Resource Recovery Handbook 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8175157
求助须知:如何正确求助?哪些是违规求助? 9566955
关于积分的说明 21789278
捐赠科研通 7769593
什么是DOI,文献DOI怎么找? 3431836
关于科研通互助平台的介绍 2556078
邀请新用户注册赠送积分活动 2477241