Litcius/Paper detail

Fast Momentum Contrast Learning for Unsupervised Person Re-Identification

Binquan Wang, Guoqi Ma, Ming Zhu

2021IEEE Signal Processing Letters16 citationsDOI

Abstract

Person re-identification (re-ID) aims to identify the same persons' images across different cameras by deploying a trained re-ID model. Nevertheless, the domain bias between different datasets can lead to considerably low identification accuracy when directly applying a trained re-ID model from one dataset to another. Therefore, in order to develop a kind of more transferable re-ID methods with strong robustness, this paper proposes a fast momentum contrast learning framework, which consists of a teacher encoder and a fast momentum encoder, from a reinforcing visual representation learning point of view. The fast momentum encoder produced by the teacher encoder is employed to build a dynamic dictionary and then design the contrast learning loss function together with the teacher encoder. In addition, both the individual loss and the clustering loss are adopted for obtaining the optimal performances in unsupervised person re-ID models. The proposed framework achieves one stage of end-to-end training and experimental results demonstrate that our identification accuracy outperforms existing advanced methods.

Topics & Concepts

Computer scienceEncoderCluster analysisRobustness (evolution)Artificial intelligenceAutoencoderContrast (vision)Unsupervised learningIdentification (biology)Machine learningPattern recognition (psychology)Feature learningRepresentation (politics)Computer visionDeep learningOperating systemBiochemistryPolitical sciencePoliticsBiologyChemistryBotanyLawGeneVideo Surveillance and Tracking MethodsAdvanced Neural Network ApplicationsHuman Pose and Action Recognition
Fast Momentum Contrast Learning for Unsupervised Person Re-Identification | Litcius