TY  - GEN
Y1  - 2019/09/02/
PB  - Springer
A1  - Ponce-Lopez, V
A1  - Burghardt, T
A1  - Sun, Y
A1  - Hannuna, S
A1  - Damen, D
A1  - Mirmehdi, M
EP  - 498
AV  - public
ID  - discovery10115347
N1  - This version is the author accepted manuscript. For information on re-use, please refer to the publisher?s terms and conditions.
SN  - 1611-3349
CY  - Cham, Switzerland
T3  - Lecture Notes in Computer Science
N2  - 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.
KW  - Person Re-ID
KW  -  GANs
KW  -  Distractor synthesis
KW  -  Deep face analysis
TI  - Deep Compact Person Re-Identification with Distractor Synthesis via Guided DC-GANs
UR  - https://doi.org/10.1007/978-3-030-30642-7_44
SP  - 488
ER  -