Person Re-Identification with a Locally Aware Transformer
| dc.contributor.author | Sharma, Charu | |
| dc.contributor.author | Kapil, Siddhant R. | |
| dc.contributor.author | Chapman, David | |
| dc.date.accessioned | 2021-06-25T19:36:38Z | |
| dc.date.available | 2021-06-25T19:36:38Z | |
| dc.date.issued | 2021-06-08 | |
| dc.description.abstract | Person Re-Identification is an important problem in computer vision-based surveillance applications, in which the same person is attempted to be identified from surveillance photographs in a variety of nearby zones. At present, the majority of Person re-ID techniques are based on Convolutional Neural Networks (CNNs), but Vision Transformers are beginning to displace pure CNNs for a variety of object recognition tasks. The primary output of a vision transformer is a global classification token, but vision transformers also yield local tokens which contain additional information about local regions of the image. Techniques to make use of these local tokens to improve classification accuracy are an active area of research. We propose a novel Locally Aware Transformer (LA-Transformer) that employs a Parts-based Convolution Baseline (PCB)-inspired strategy for aggregating globally enhanced local classification tokens into an ensemble of Nāāā classifiers, where N is the number of patches. An additional novelty is that we incorporate blockwise fine-tuning which further improves re-ID accuracy. LA-Transformer with blockwise fine-tuning achieves rank-1 accuracy of 98.27% with standard deviation of 0.13 on the Market-1501 and 98.7% with standard deviation of 0.2 on the CUHK03 dataset respectively, outperforming all other state-of-the-art published methods at the time of writing. | en_US |
| dc.description.uri | https://arxiv.org/abs/2106.03720 | en_US |
| dc.format.extent | 10 pages | en_US |
| dc.genre | journal articles preprints | en_US |
| dc.identifier | doi:10.13016/m2kqmp-wxwl | |
| dc.identifier.citation | Sharma, Charu; Kapil, Siddhant R.; Chapman, David; Person Re-Identification with a Locally Aware Transformer; Computer Vision and Pattern Recognition, 8 June, 2021; https://arxiv.org/abs/2106.03720 | en_US |
| dc.identifier.uri | http://hdl.handle.net/11603/21829 | |
| dc.language.iso | en_US | en_US |
| dc.relation.isAvailableAt | The University of Maryland, Baltimore County (UMBC) | |
| dc.relation.ispartof | UMBC Computer Science and Electrical Engineering Department Collection | |
| dc.relation.ispartof | UMBC Faculty Collection | |
| dc.relation.ispartof | UMBC Student Collection | |
| dc.rights | This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author. | |
| dc.rights | Attribution 4.0 International (CC BY 4.0) | * |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | * |
| dc.title | Person Re-Identification with a Locally Aware Transformer | en_US |
| dc.type | Text | en_US |