Ponce-Lopez, V; Burghardt, T; Sun, Y; Hannuna, S; Damen, D; Mirmehdi, M; (2019) Deep Compact Person Re-Identification with Distractor Synthesis via Guided DC-GANs. In: Ricci, E and Bulo, SR and Snoek, C and Lanz, O and Messelodi, S and Sebe, N, (eds.) Image Analysis and Processing – ICIAP 2019. ICIAP 2019. (pp. pp. 488-498). Springer: Cham, Switzerland.

Preview

Text Ponce Lopez_ICIAP19_Guided-DC-GANs_CameraReady.pdf - Accepted Version Download (3MB) | Preview

Abstract

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.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as XMLCSVJSON

Archive Staff Only

View Item