TY - GEN
T1 - Camera On-Boarding for Person Re-Identification Using Hypothesis Transfer Learning
AU - Ahmed, Sk Miraj
AU - Lejbølle, Aske Rasch
AU - Panda, Rameswar
AU - Chowdhury, Amit K. Roy
PY - 2020
Y1 - 2020
N2 - Most of the existing approaches for person re-identification consider a static setting where the number of cameras in the network is fixed. An interesting direction, which has received little attention, is to explore the dynamic nature of a camera network, where one tries to adapt the existing re-identification models after on-boarding new cameras, with little additional effort. There have been a few recent methods proposed in person re-identification that attempt to address this problem by assuming the labeled data in the existing network is still available while adding new cameras. This is a strong assumption since there may exist some privacy issues for which one may not have access to those data. Rather, based on the fact that it is easy to store the learned re-identifications models, which mitigates any data privacy concern, we develop an efficient model adaptation approach using hypothesis transfer learning that aims to transfer the knowledge using only source models and limited labeled data, but without using any source camera data from the existing network. Our approach minimizes the effect of negative transfer by finding an optimal weighted combination of multiple source models for transferring the knowledge. Extensive experiments on four challenging benchmark datasets with variable number of cameras well demonstrate the efficacy of our proposed approach over state-of-the-art methods.
AB - Most of the existing approaches for person re-identification consider a static setting where the number of cameras in the network is fixed. An interesting direction, which has received little attention, is to explore the dynamic nature of a camera network, where one tries to adapt the existing re-identification models after on-boarding new cameras, with little additional effort. There have been a few recent methods proposed in person re-identification that attempt to address this problem by assuming the labeled data in the existing network is still available while adding new cameras. This is a strong assumption since there may exist some privacy issues for which one may not have access to those data. Rather, based on the fact that it is easy to store the learned re-identifications models, which mitigates any data privacy concern, we develop an efficient model adaptation approach using hypothesis transfer learning that aims to transfer the knowledge using only source models and limited labeled data, but without using any source camera data from the existing network. Our approach minimizes the effect of negative transfer by finding an optimal weighted combination of multiple source models for transferring the knowledge. Extensive experiments on four challenging benchmark datasets with variable number of cameras well demonstrate the efficacy of our proposed approach over state-of-the-art methods.
UR - http://www.scopus.com/inward/record.url?scp=85094809079&partnerID=8YFLogxK
U2 - 10.1109/CVPR42600.2020.01216
DO - 10.1109/CVPR42600.2020.01216
M3 - Article in proceeding
SN - 978-1-7281-7169-2
T3 - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings
SP - 12141
EP - 12150
BT - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition
PB - IEEE
T2 - 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Y2 - 14 June 2020 through 19 June 2020
ER -