dc.contributor.author | Li, Q | |
dc.contributor.author | Huang, J | |
dc.contributor.author | Hu, J | |
dc.contributor.author | Gong, S | |
dc.contributor.author | ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | |
dc.date.accessioned | 2024-06-25T08:00:31Z | |
dc.date.available | 2024-06-25T08:00:31Z | |
dc.date.issued | 2024-04-14 | |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/97659 | |
dc.description.abstract | Person Re-identification (ReID) has been advanced remarkably over the last 10 years. However, the i.i.d. (independent and identically distributed) assumption is somewhat non-applicable to ReID considering its objective to identify images of the same pedestrian across cameras at different locations. In this work, we propose a Feature-Distribution Perturbation and Calibration (PECA) method to derive generic feature representations for person ReID. Specifically, we perform per-domain feature-distribution perturbation to refrain the model from overfitting to the domain-biased distribution of each source (seen) domain by enforcing feature invariance to distribution shifts caused by perturbation. Furthermore, we design a global calibration mechanism to align feature distributions across all the source domains to improve the model’s generalization capacity by eliminating domain bias. These local perturbation and global calibration are conducted simultaneously, which share the same principle to avoid models overfitting by regularization respectively on the perturbed and the original distributions. Extensive experiments were conducted and the proposed PECA model outperformed the state-of-the-art competitors by significant margins. | en_US |
dc.format.extent | 2880 - 2884 | |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_US |
dc.title | Feature-Distribution Perturbation and Calibration for Generalized Reid | en_US |
dc.type | Conference Proceeding | en_US |
dc.rights.holder | © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | |
dc.identifier.doi | 10.1109/icassp48485.2024.10448017 | |
pubs.notes | Not known | en_US |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |