Optimizing speed/accuracy trade-off for person re-identification via knowledge distillation

Idoia Ruiz, Bogdan Raducanu, Rakesh Mehta, Jaume Amores

Research output: Contribution to journalArticleResearchpeer-review

2 Citations (Scopus)

Abstract

© 2019 Elsevier Ltd Finding a person across a camera network plays an important role in video surveillance. For a real-world person re-identification application, in order to guarantee an optimal time response, it is crucial to find the balance between accuracy and speed. We analyse this trade-off, comparing a classical method, that comprises hand-crafted feature description and metric learning, in particular, LOMO and XQDA, to deep learning based techniques, using image classification networks, ResNet and MobileNets. Additionally, we propose and analyse network distillation as a learning strategy to reduce the computational cost of the deep learning approach at test time. We evaluate both methods on the Market-1501 and DukeMTMC-reID large-scale datasets, showing that distillation helps reducing the computational cost at inference time while even increasing the accuracy performance.
Original languageEnglish
Article number103309
Number of pages11
JournalEngineering Applications of Artificial Intelligence
Volume87
DOIs
Publication statusPublished - 1 Jan 2020

Keywords

  • Image retrieval
  • Model compression
  • Network distillation
  • Person re-identification
  • Surveillance

Fingerprint

Dive into the research topics of 'Optimizing speed/accuracy trade-off for person re-identification via knowledge distillation'. Together they form a unique fingerprint.

Cite this