Person Re-Identification using Deep Convnets with Multi-task Learning

Research output: Contribution to journalArticlepeer-review

31 Citations (Scopus)
1099 Downloads (Pure)

Abstract

Person re-identification involves recognizing a person across non-overlapping camera views, with different pose, illumination, and camera characteristics. We propose to tackle this problem by training a deep convolutional network to represent a person’s appearance as a low-dimensional feature vector that is invariant to common appearance variations encountered in the re-identification problem. Specifically, a Siamese-network architecture is used to train a feature extraction network using pairs of similar and dissimilar images. We show that use of a novel multi-task learning objective is crucial for regularizing the network parameters in order to prevent over-fitting due to the small size the training dataset. We complement the verification task, which is at the heart of re-identification, by training the network to jointly perform verification, identification, and to recognise attributes related to the clothing and pose of the person in each image. Additionally, we show that our proposed approach performs well even in the challenging cross-dataset scenario, which may better reflect real-world expected performance. 
Original languageEnglish
Pages (from-to)525-539
Number of pages14
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume27
Issue number3
Early online date20 Oct 2016
DOIs
Publication statusPublished - Mar 2017

Fingerprint

Dive into the research topics of 'Person Re-Identification using Deep Convnets with Multi-task Learning'. Together they form a unique fingerprint.

Cite this