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.
|Title of host publication||International Conference on Image Analysis and Processing|
|Subtitle of host publication||Lecture Notes in Computer Science|
|Number of pages||11|
|Publication status||Published - 2 Sep 2019|
|Name||Lecture Notes in Computer Science|
- Digital Health
Ponce Lopez, V., Burghardt, T., Sun, Y., Hannuna, S., Aldamen, D., & Mirmehdi, M. (2019). Deep Compact Person Re-Identification with Distractor Synthesis via Guided DC-GANs. In International Conference on Image Analysis and Processing: Lecture Notes in Computer Science (Vol. 11751, pp. 488-498). (Lecture Notes in Computer Science; Vol. 11751). Springer. https://doi.org/10.1007/978-3-030-30642-7_44