Deep Compact Person Re-Identification with Distractor Synthesis via Guided DC-GANs

Victor Ponce Lopez, Tilo Burghardt, Yue Sun, Sion Hannuna, Dima Aldamen, Majid Mirmehdi

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)


We present a dual-stream CNN that learns both appearance and facial features in tandem from still images and, after feature fusion, infers person identities. We then describe an alternative architecture of a single, lightweight ID-CondenseNet where a face detector-guided DC-GAN is used to generate distractor person images for enhanced training. For evaluation, we test both architectures on FLIMA, a new extension of an existing person re-identification dataset with added frame-by-frame annotations of face presence. Although the dual-stream CNN can outperform the CondenseNet approach on FLIMA, we show that the latter surpasses all state-of-the-art architectures in top-1 ranking performance when applied to the largest existing person re-identification dataset, MSMT17. We conclude that whilst re-identification performance is highly sensitive to the structure of datasets, distractor augmentation and network compression have a role to play for enhancing performance characteristics for larger scale applications.
Original languageEnglish
Title of host publicationInternational Conference on Image Analysis and Processing
Subtitle of host publicationLecture Notes in Computer Science
Number of pages11
ISBN (Electronic)9783030306427
ISBN (Print)9783030306410
Publication statusPublished - 2 Sept 2019

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Cham
ISSN (Electronic)0302-9743

Structured keywords

  • Digital Health


Dive into the research topics of 'Deep Compact Person Re-Identification with Distractor Synthesis via Guided DC-GANs'. Together they form a unique fingerprint.

Cite this