PARTITION AND REUNION: A VIEWPOINT-AWARE LOSS FOR VEHICLE RE-IDENTIFICATION

Haobo Chen, Yang Liu, Yang Huang, Wei Ke, Hao Sheng

研究成果: Conference contribution同行評審

5 引文 斯高帕斯(Scopus)

摘要

Vehicle Re-Identification (ReID) aims to retrieve images of vehicles with the same identity from different scenarios. It is a challenging task due to the large intra-identity discrepancy caused by viewpoint variations and the subtle inter-identity difference produced by similar appearances. In this paper, we propose a Viewpoint-Aware Loss (VAL) function to deal with these challenges. Specifically, we propose partition and reunion operations in VAL, which significantly shrinks the intra-identity distance and acquires viewpoint-invariant representations. In addition, we embed a multi-decision boundary mechanism in VAL. It contributes to enlarging the inter-identity distance. A comprehensive evaluation on two benchmarks shows the superiority of our method in contrast to a series of existing state-of-the-arts.

原文English
主出版物標題2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
發行者IEEE Computer Society
頁面2246-2250
頁數5
ISBN(電子)9781665496209
DOIs
出版狀態Published - 2022
事件29th IEEE International Conference on Image Processing, ICIP 2022 - Bordeaux, France
持續時間: 16 10月 202219 10月 2022

出版系列

名字Proceedings - International Conference on Image Processing, ICIP
ISSN(列印)1522-4880

Conference

Conference29th IEEE International Conference on Image Processing, ICIP 2022
國家/地區France
城市Bordeaux
期間16/10/2219/10/22

指紋

深入研究「PARTITION AND REUNION: A VIEWPOINT-AWARE LOSS FOR VEHICLE RE-IDENTIFICATION」主題。共同形成了獨特的指紋。

引用此