TY - GEN
T1 - Compact network training for person ReID
AU - Lawen, Hussam
AU - Ben-Cohen, Avi
AU - Protter, Matan
AU - Friedman, Itamar
AU - Zelnik-Manor, Lihi
N1 - Publisher Copyright:
© 2020 ACM.
PY - 2020/6/8
Y1 - 2020/6/8
N2 - The task of person re-identification (ReID) has attracted growing attention in recent years leading to improved performance, albeit with little focus on real-world applications. Most SotA methods are based on heavy pre-trained models, e.g. ResNet50 (∼25M parameters), which makes them less practical and more tedious to explore architecture modifications. In this study, we focus on a small-sized randomly initialized model that enables us to easily introduce architecture and training modifications suitable for person ReID. The outcomes of our study are a compact network and a fitting training regime. We show the robustness of the network by outperforming the SotA on both Market1501 and DukeMTMC. Furthermore, we show the representation power of our ReID network via SotA results on a different task of multi-object tracking.
AB - The task of person re-identification (ReID) has attracted growing attention in recent years leading to improved performance, albeit with little focus on real-world applications. Most SotA methods are based on heavy pre-trained models, e.g. ResNet50 (∼25M parameters), which makes them less practical and more tedious to explore architecture modifications. In this study, we focus on a small-sized randomly initialized model that enables us to easily introduce architecture and training modifications suitable for person ReID. The outcomes of our study are a compact network and a fitting training regime. We show the robustness of the network by outperforming the SotA on both Market1501 and DukeMTMC. Furthermore, we show the representation power of our ReID network via SotA results on a different task of multi-object tracking.
KW - Compact network
KW - Deep person reid
KW - Multi-object tracking
UR - http://www.scopus.com/inward/record.url?scp=85086903132&partnerID=8YFLogxK
U2 - 10.1145/3372278.3390686
DO - 10.1145/3372278.3390686
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85086903132
T3 - ICMR 2020 - Proceedings of the 2020 International Conference on Multimedia Retrieval
SP - 164
EP - 171
BT - ICMR 2020 - Proceedings of the 2020 International Conference on Multimedia Retrieval
PB - Association for Computing Machinery, Inc
T2 - 10th ACM International Conference on Multimedia Retrieval, ICMR 2020
Y2 - 8 June 2020 through 11 June 2020
ER -