Litcius/Paper detail

A sample‐proxy dual triplet loss function for object re‐identification

Hanxiao Wu, Fei Shen, Jianqing Zhu, Huanqiang Zeng, Xiaobin Zhu, Zhen Lei

2022IET Image Processing20 citationsDOIOpen Access PDF

Abstract

Abstract Object re‐identification, such as vehicle re‐identification or pedestrian re‐identification, plays a significant role in intelligent video surveillance systems for public security. Due to viewpoint variations and appearance changes, both pedestrians and vehicles usually have complex intra‐class variations. However, most existing object re‐identification methods often use a sample‐level triplet loss function cooperating with a single‐proxy softmax loss function, which could not handle complex intra‐class variations well. In this paper, a sample‐proxy dual triplet (SPDT) loss function is proposed, which works with a multi‐proxy softmax (MPS) loss function. The MPS loss function is in charge of learning multiple proxies to represent a class. The SPDT loss function is responsible for enlarging inter‐class distances as well as shrinking intra‐class distances on both sample and proxy levels. Therefore, the method not only handles multi‐proxy intra‐class variations but also fully learns discrimination on samples and proxies. Experiments on two large datasets, that is, VeRi776 and DukeMTMC‐reID, demonstrate that the method is superior to state‐of‐the‐art object re‐identification approaches.

Topics & Concepts

Proxy (statistics)Dual (grammatical number)Dual functionIdentification (biology)Computer scienceObject (grammar)Function (biology)Sample (material)Pattern recognition (psychology)Artificial intelligenceMachine learningChemistryComputer graphics (images)ChromatographyBiologyArtBotanyLiteratureContouringEvolutionary biologyAdvanced Image and Video Retrieval TechniquesVideo Surveillance and Tracking MethodsImage Enhancement Techniques
A sample‐proxy dual triplet loss function for object re‐identification | Litcius