Performance Comparison of Backbone Networks for Multi-Tasking in Self-Driving Operations

计算机科学 骨干网 任务(项目管理) 推论 分割 人工智能 目标检测 深度学习 任务分析 人工神经网络 网络体系结构 对象(语法) 机器学习 实时计算 计算机网络 工程类 系统工程
作者
Shakhboz Abdigapporov,Shokhrukh Miraliev,Jumabek Alikhanov,Vijay Kakani,Hakil Kim
标识
DOI:10.23919/iccas55662.2022.10003816
摘要

In the era of big data, increased focus has been on improving neural network based Deep Learning models. This led to various classification networks which can be used as a backbone in multi-task learning. However, depending on the selected backbone, multi-tasking performance differs. While given backbone network shows better performance on a detection task, does not mean such performance generalizes in segmentation task as well. Detailed investigations should be conducted to achieve best inference speed-accuracy trade-off prior to implementing a single neural network, which handles multiple tasks. In this research, the performance comparison among EfficientNet, ResNet101, VGG16, ResNet50 and MobilenetV2 on the Berkeley Driving Dataset (BDD100K) for autonomous driving using multi-tasking architecture are provided. Backbones that offer best time-accuracy trade-off for multi-task learning are evaluated. Implemented architecture contains three most crucial tasks in self-driving operations, object detection, drivable area segmentation and lane detection. EfficientNet based model showed the best mAP on the object detection task, as well as on the segmentation tasks, extracting both the long and wide roads with accurate lane lines. The model with MobilenetV2 backbone however, demonstrates the fastest inference speed with relatively lower performance in all tasks.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
cc发布了新的文献求助30
刚刚
Zed关闭了Zed文献求助
刚刚
1秒前
1秒前
fjc发布了新的文献求助10
1秒前
小青完成签到 ,获得积分10
1秒前
2秒前
一枚研究僧完成签到,获得积分0
2秒前
2秒前
guons完成签到 ,获得积分10
2秒前
yrq关注了科研通微信公众号
3秒前
to高坚果发布了新的文献求助10
3秒前
合适的毛豆完成签到,获得积分10
3秒前
顾矜应助Ing采纳,获得10
3秒前
torch132完成签到,获得积分10
3秒前
小二郎应助科研通管家采纳,获得10
3秒前
爆米花应助科研通管家采纳,获得10
3秒前
传奇3应助科研通管家采纳,获得10
3秒前
深情的友易完成签到 ,获得积分10
4秒前
脑洞疼应助科研通管家采纳,获得10
4秒前
科研通AI2S应助科研通管家采纳,获得30
4秒前
在水一方应助科研通管家采纳,获得10
4秒前
顾矜应助科研通管家采纳,获得10
4秒前
风趣初瑶应助科研通管家采纳,获得10
4秒前
领导范儿应助科研通管家采纳,获得10
4秒前
CipherSage应助科研通管家采纳,获得30
4秒前
4秒前
4秒前
4秒前
4秒前
4秒前
mryun完成签到,获得积分10
5秒前
5秒前
tian发布了新的文献求助20
5秒前
5秒前
llllllll发布了新的文献求助10
5秒前
否认冶游史完成签到,获得积分10
5秒前
英姑应助渔夫采纳,获得10
5秒前
聂聪发布了新的文献求助10
6秒前
请叫我风吹麦浪应助猫猫采纳,获得10
6秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968964
求助须知:如何正确求助?哪些是违规求助? 3513877
关于积分的说明 11170569
捐赠科研通 3249201
什么是DOI,文献DOI怎么找? 1794692
邀请新用户注册赠送积分活动 875297
科研通“疑难数据库(出版商)”最低求助积分说明 804755