Qiu, Liuxiang;
Chen, Si;
Yan, Yan;
Xue, Jing-Hao;
Wang, Da-Han;
Zhu, Shunzhi;
(2024)
High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-Identification.
In:
Proceedings of the AAAI Conference on Artificial Intelligence.
(pp. pp. 4596-4604).
AAAI: Vancouver, Canada.
Preview |
Text
2312.07853.pdf - Accepted Version Download (6MB) | Preview |
Abstract
Visible-infrared person re-identification (VI-ReID) aims to retrieve images of the same persons captured by visible (VIS) and infrared (IR) cameras. Existing VI-ReID methods ignore high-order structure information of features while being relatively difficult to learn a reasonable common feature space due to the large modality discrepancy between VIS and IR images. To address the above problems, we propose a novel high-order structure based middle-feature learning network (HOS-Net) for effective VI-ReID. Specifically, we first leverage a short- and long-range feature extraction (SLE) module to effectively exploit both short-range and long-range features. Then, we propose a high-order structure learning (HSL) module to successfully model the high-order relationship across different local features of each person image based on a whitened hypergraph network. This greatly alleviates model collapse and enhances feature representations. Finally, we develop a common feature space learning (CFL) module to learn a discriminative and reasonable common feature space based on middle features generated by aligning features from different modalities and ranges. In particular, a modality-range identity-center contrastive (MRIC) loss is proposed to reduce the distances between the VIS, IR, and middle features, smoothing the training process. Extensive experiments on the SYSU-MM01, RegDB, and LLCM datasets show that our HOS-Net achieves superior state-ofthe-art performance. Our code is available at https://github. com/Jaulaucoeng/HOS-Net.
| Type: | Proceedings paper |
|---|---|
| Title: | High-Order Structure Based Middle-Feature Learning for Visible-Infrared Person Re-Identification |
| Event: | The 38th Annual AAAI Conference on Artificial Intelligence |
| Dates: | 22 Feb 2024 - 25 Feb 2024 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1609/aaai.v38i5.28259 |
| Publisher version: | https://doi.org/10.1609/aaai.v38i5.28259 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10187927 |
Archive Staff Only
 |
View Item |
