UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Semantically selective augmentation for deep compact person re-identification

Ponce-López, V; Burghardt, T; Hannunna, S; Damen, D; Masullo, A; Mirmehdi, M; (2019) Semantically selective augmentation for deep compact person re-identification. In: Computer Vision – ECCV 2018 Workshops. ECCV 2018. (pp. pp. 551-561). Springer: Cham, Switzerland. Green open access

[thumbnail of Ponce Lopez_eccvw-pic-2018_cameraReady.pdf]
Preview
Text
Ponce Lopez_eccvw-pic-2018_cameraReady.pdf - Accepted Version

Download (1MB) | Preview

Abstract

We present a deep person re-identification approach that combines semantically selective, deep data augmentation with clustering-based network compression to generate high performance, light and fast inference networks. In particular, we propose to augment limited training data via sampling from a deep convolutional generative adversarial network (DCGAN), whose discriminator is constrained by a semantic classifier to explicitly control the domain specificity of the generation process. Thereby, we encode information in the classifier network which can be utilized to steer adversarial synthesis, and which fuels our CondenseNet ID-network training. We provide a quantitative and qualitative analysis of the approach and its variants on a number of datasets, obtaining results that outperform the state-of-the-art on the LIMA dataset for long-term monitoring in indoor living spaces.

Type: Proceedings paper
Title: Semantically selective augmentation for deep compact person re-identification
ISBN-13: 9783030110116
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-030-11012-3_41
Publisher version: https://doi.org/10.1007/978-3-030-11012-3_41
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Person re-identification, Selective augmentation, Face filtering, Adversarial synthesis, Deep compression
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment > Bartlett School Env, Energy and Resources
URI: https://discovery.ucl.ac.uk/id/eprint/10115349
Downloads since deposit
44Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item