Rank-in-Rank Loss for Person Re-identification

秩(图论) 排名(信息检索) 分类 分类 可微函数 相似性(几何) 特征(语言学) 计算机科学 人工智能 班级(哲学) 鉴定(生物学) 模式识别(心理学) 数学 算法 图像(数学) 组合数学 数学分析 语言学 哲学 植物 生物 情报检索
作者
Xin Xu,Xin Yuan,Zheng Wang,Kai Zhang,Ruimin Hu
出处
期刊:ACM Transactions on Multimedia Computing, Communications, and Applications [Association for Computing Machinery]
卷期号:18 (2s): 1-21 被引量:7
标识
DOI:10.1145/3532866
摘要

Person re-identification (re-ID) is commonly investigated as a ranking problem. However, the performance of existing re-ID models drops dramatically, when they encounter extreme positive-negative class imbalance (e.g., very small ratio of positive and negative samples) during training. To alleviate this problem, this article designs a rank-in-rank loss to optimize the distribution of feature embeddings. Specifically, we propose a Differentiable Retrieval-Sort Loss (DRSL) to optimize the re-ID model by ranking each positive sample ahead of the negative samples according to the distance and sorting the positive samples according to the angle (e.g., similarity score). The key idea of the proposed DRSL lies in minimizing the distance between samples of the same category along with the angle between them. Considering that the ranking and sorting operations are non-differentiable and non-convex, the DRSL also performs the optimization of automatic derivation and backpropagation. In addition, the analysis of the proposed DRSL is provided to illustrate that the DRSL not only maintains the inter-class distance distribution but also preserves the intra-class similarity structure in terms of angle constraints. Extensive experimental results indicate that the proposed DRSL can improve the performance of the state-of-the-art re-ID models, thus demonstrating its effectiveness and superiority in the re-ID task.
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
大幅提高文件上传限制,最高150M (2024-4-1)

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
1秒前
木光发布了新的文献求助10
1秒前
1秒前
小白应助1163125682采纳,获得30
2秒前
2秒前
yanzu应助温柔的海安采纳,获得10
4秒前
4秒前
Jasper应助甜甜盼夏采纳,获得10
5秒前
7秒前
7秒前
英俊的铭应助桃园采纳,获得10
7秒前
9秒前
9秒前
王大壮完成签到,获得积分10
10秒前
czq发布了新的文献求助10
10秒前
12秒前
12秒前
我不看月亮完成签到,获得积分10
12秒前
星辰大海应助DrD采纳,获得10
12秒前
看不懂文献的进士完成签到,获得积分10
13秒前
南波万发布了新的文献求助10
14秒前
14秒前
14秒前
human发布了新的文献求助10
16秒前
16秒前
16秒前
大个应助1111采纳,获得10
18秒前
的微博发布了新的文献求助10
19秒前
20秒前
20秒前
专注凌文完成签到,获得积分10
20秒前
21秒前
21秒前
czq完成签到,获得积分10
22秒前
cxzhao完成签到,获得积分10
22秒前
binbin发布了新的文献求助10
22秒前
听话的靖柏完成签到 ,获得积分10
23秒前
23秒前
璐璐发布了新的文献求助10
24秒前
24秒前
高分求助中
One Man Talking: Selected Essays of Shao Xunmei, 1929–1939 1000
A Chronicle of Small Beer: The Memoirs of Nan Green 1000
From Rural China to the Ivy League: Reminiscences of Transformations in Modern Chinese History 900
Eric Dunning and the Sociology of Sport 850
QMS18Ed2 | process management. 2nd ed 800
Operative Techniques in Pediatric Orthopaedic Surgery 510
The Making of Détente: Eastern Europe and Western Europe in the Cold War, 1965-75 500
热门求助领域 (近24小时)
化学 医学 材料科学 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 基因 遗传学 物理化学 催化作用 免疫学 细胞生物学 电极
热门帖子
关注 科研通微信公众号,转发送积分 2915101
求助须知:如何正确求助?哪些是违规求助? 2553165
关于积分的说明 6907925
捐赠科研通 2214957
什么是DOI,文献DOI怎么找? 1177487
版权声明 588353
科研通“疑难数据库(出版商)”最低求助积分说明 576390