Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification
Authors:
- 16 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 16870-16879
Abstract
Unsupervised visible-infrared person re-identification (US-VI-ReID) centers on learning a cross-modality retrieval model without labels, reducing the reliance on expensive cross-modality manual annotation. Previous US-VI-ReID works gravitate toward learning cross-modality information with the deep features extracted from the ultimate layer. Nevertheless, interfered by the multiple discrepancies, solely relying on deep features is insufficient for accurately learning modality-invariant features, resulting in negative optimization. The shallow feature from the shallow layers contains nuanced detail information, which is critical for effective cross-modality learning but is dis- regarded regrettably by the existing methods. To address the above issues, we design a Shallow-Deep Collaborative Learning (SDCL) framework based on the transformer with shallow-deep contrastive learning, incorporating Collaborative Neighbor Learning (CNL) and Collaborative Ranking Association (CRA) module. Specifically, CNL unveils the intrinsic homogeneous and heterogeneous collaboration which are harnessed for neighbor alignment, enhancing the robustness in a dynamic manner. Furthermore, CRA associates the cross-modality labels with the ranking association between shallow and deep features, furnishing valuable supervision for cross-modality learning. Extensive experiments validate the superiority of our method, even outperforming certain supervised counterparts.Keywords
Funding Information
- National Natural Science Foundation of China (62071338,62176188,62272354,62306215)
- Renmin Hospital of Wuhan University
This publication has 50 references indexed in Scilit:
- Visible–infrared person re-identification via patch-mixed cross-modality learningPattern Recognition, 2024
- Multi‐granularity re‐ranking for visible‐infrared person re‐identificationCAAI Transactions on Intelligence Technology, 2023
- Optimal Transport for Label-Efficient Visible-Infrared Person Re-Identification2022
- FMCNet: Feature-Level Modality Compensation for Visible-Infrared Person Re-Identification2022
- Part-based Pseudo Label Refinement for Unsupervised Person Re-identification2022
- Discover Cross-Modality Nuances for Visible-Infrared Person Re-Identification2021
- Intra-Inter Camera Similarity for Unsupervised Person Re-Identification2021
- Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-identification2020
- Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer2020
- Learning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-Identification2019