Cross-view Discriminative Feature Learning for Person Re-Identification

Alessandro Borgia, Yang Hua, Elyor Kodirov, Neil Robertson

Research output: Contribution to journalArticle

10 Citations (Scopus)
391 Downloads (Pure)

Abstract

The viewpoint variability across a network of nonoverlapping cameras is a challenging problem affecting person re-identification performance. In this paper, we investigate how to mitigate the cross-view ambiguity by learning highly discriminative deep features under the supervision of a novel loss function. The proposed objective is made up of two terms, the Steering Meta Center (SMC) term and the Enhancing Centres Dispersion (ECD) term that steer the training process to mining effective intra-class and inter-class relationships in the feature domain of the identities. The effect of our loss supervision is to generate a more expanded feature space of compact classes where the overall level of inter-identities interference is reduced. Compared to the existing metric learning techniques, this approach has the advantage of achieving a better optimization because it jointly learns the embedding and the metric contextually. Our technique, by dismissing side-sources of performance gain, proves to enhance the CNN invariance to viewpoint without incurring increased training complexity (like in Siamese or Triplet networks) and outperforms many related state-of-the-art techniques on Market- 1501 and CUHK03.
Original languageEnglish
Pages (from-to)5338 - 5349
JournalIEEE Trans. on Image Processing
Volume27
Issue number11
Early online date27 Jun 2018
DOIs
Publication statusPublished - Nov 2018

Fingerprint Dive into the research topics of 'Cross-view Discriminative Feature Learning for Person Re-Identification'. Together they form a unique fingerprint.

  • Cite this