Skip to content

Semantically Selective Augmentation for Deep Compact Person Re-Identification

Research output: Chapter in Book/Report/Conference proceedingChapter in a book

Original languageEnglish
Title of host publicationComputer Vision – ECCV 2018 Workshops
Publisher or commissioning bodySpringer, Cham
Pages551-561
Volume11130
ISBN (Electronic)978-3-030-11012-3
ISBN (Print)978-3-030-11011-6
DOIs
DatePublished - 29 Jan 2019

Publication series

NameLecture Notes in Computer Science
PublisherSpringer, Cham
Volume11130
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

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.

Documents

View research connections

Related faculties, schools or groups