Multi-attribute adaptive aggregation transformer for vehicle re-identification

计算机科学 变压器 编码 人工智能 车辆跟踪系统 特征提取 计算机视觉 特征(语言学) 模式识别(心理学) 数据挖掘 工程类 分割 基因 电气工程 哲学 生物化学 电压 化学 语言学
作者
Zhi Yu,Jiaming Pei,Mingpeng Zhu,Jiwei Zhang,Jinhai Li
出处
期刊:Information Processing and Management [Elsevier BV]
卷期号:59 (2): 102868-102868 被引量:52
标识
DOI:10.1016/j.ipm.2022.102868
摘要

• A vehicle attribute transformer for vehicle re-identification is proposed, which can aggregate the attributes of vehicle model, color and viewpoint adaptively. • A multi-sample dispersion triplet loss is designed to optimize the proposed transformer network, which can consider richer positive and negative sample information. • Extensive experiments on popular vehicle re-identification datasets verify that the proposed method can achieve state-of-the-art performance. With the continuous development of intelligent transportation systems, vehicle-related fields have emerged a research boom in detection, tracking, and retrieval. Vehicle re-identification aims to judge whether a specific vehicle appears in a video stream, which is a popular research direction. Previous researches have proven that the transformer is an efficient method in computer vision, which treats a visual image as a series of patch sequences. However, an efficient vehicle re-identification should consider the image feature and the attribute feature simultaneously. In this work, we propose a vehicle attribute transformer (VAT) for vehicle re-identification. First, we consider color and model as the most intuitive attributes of the vehicle, the vehicle color and model are relatively stable and easy to distinguish. Therefore, the color feature and the model feature are embedded in a transformer. Second, we consider that the shooting angle of each image may be different, so we encode the viewpoint of the vehicle image as another additional attribute. Besides, different attributes are supposed to have different importance. Based on this, we design a multi-attribute adaptive aggregation network, which can compare different attributes and assign different weights to the corresponding features. Finally, to optimize the proposed transformer network, we design a multi-sample dispersion triplet (MDT) loss. Not only the hardest samples based on hard mining strategy, but also some extra positive samples and negative samples are considered in this loss. The dispersion of multi-sample is utilized to dynamically adjust the loss, which can guide the network to learn more optimized division for feature space. Extensive experiments on popular vehicle re-identification datasets verify that the proposed method can achieve state-of-the-art performance.
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
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
842413119完成签到,获得积分10
1秒前
大个应助暖暖采纳,获得20
1秒前
赘婿应助huanhuan采纳,获得10
1秒前
xinxinqi完成签到 ,获得积分10
3秒前
木今完成签到,获得积分10
3秒前
wanci应助msli采纳,获得10
9秒前
火龙果完成签到,获得积分10
11秒前
高高发布了新的文献求助10
14秒前
14秒前
留胡子的如花完成签到,获得积分10
15秒前
15秒前
15秒前
15秒前
田様应助bobo采纳,获得10
17秒前
zhouyan完成签到,获得积分10
20秒前
llchen完成签到,获得积分0
20秒前
huanhuan发布了新的文献求助10
20秒前
20秒前
21秒前
msli发布了新的文献求助10
21秒前
23秒前
linmu完成签到 ,获得积分10
23秒前
科研兄完成签到,获得积分10
24秒前
tian发布了新的文献求助10
25秒前
科研兄发布了新的文献求助10
26秒前
front完成签到,获得积分10
28秒前
风轻云淡发布了新的文献求助10
28秒前
欧阳静芙完成签到,获得积分10
28秒前
Melody完成签到,获得积分10
29秒前
jiapei_1019发布了新的文献求助10
31秒前
31秒前
刘企盼完成签到,获得积分10
32秒前
32秒前
33秒前
传奇3应助风轻云淡采纳,获得10
35秒前
大个应助无限妙梦采纳,获得10
35秒前
沈括完成签到,获得积分10
35秒前
36秒前
37秒前
37秒前
高分求助中
Encyclopedia of Mathematical Physics 2nd edition 888
Technologies supporting mass customization of apparel: A pilot project 600
Hydropower Nation: Dams, Energy, and Political Changes in Twentieth-Century China 500
Introduction to Strong Mixing Conditions Volumes 1-3 500
Pharmacological profile of sulodexide 400
Optical and electric properties of monocrystalline synthetic diamond irradiated by neutrons 320
共融服務學習指南 300
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 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3805322
求助须知:如何正确求助?哪些是违规求助? 3350279
关于积分的说明 10348304
捐赠科研通 3066188
什么是DOI,文献DOI怎么找? 1683602
邀请新用户注册赠送积分活动 809099
科研通“疑难数据库(出版商)”最低求助积分说明 765225