A dual-aligned knowledge self-distillation framework for visible-infrared cross-modal person re-identification

Siyuan Deng, Kunhao Yuan, Gerald Schaefer, Shihua Zhou, George Vogiatzis, Yifan Wang and Hui Fang

Knowledge-Based Systems · 2025

Abstract

• Dual alignment knowledge self-distillation to better capture modality-invariant/specific features for VI-ReID • Temperature-modulated alignment and confidence-based selective masking to enhance model reliability. • CutSwap augmentation to improve model robustness against intra-class variations and modality discrepancies. • State-of-the-art performance on SYSU-MM01 and RegDB benchmarks. Visible-infrared person re-identification (VI-ReID) significantly enhances identity retrieval across different illumination conditions by matching visible and infrared modalities. However, existing contrastive-learning-based approaches predominantly focus on cross-modal feature alignment, thus undermining model reliability in complex scenarios. To address this challenge, we introduce a Dual Alignment Knowledge Distillation (DAKD) framework that leverages comprehensive self-distillation at both instance and class levels. Our framework incorporates a temperature-modulated alignment strategy, capturing rich modality-invariant generalities as well as modality-specific discriminative details. Additionally, we propose a confidence-based selective masking mechanism that guides the distillation towards confident and informative teacher predictions. To further enhance robustness against modality discrepancies and intra-class variations, we develop a dedicated augmentation technique, CutSwap, which exchanges image channels to simulate realistic cross-modality variations. Extensive experiments on the benchmark SYSU-MM01 and RegDB datasets demonstrate superior performance compared to other state-of-the-art methods, achieving rank-1 accuracies of 76.31% and 94.83%, respectively and validating the efficacy of DAKD in maintaining robust cross-modal alignment while preserving essential identity-specific discriminative information.

Citation

Siyuan Deng, Kunhao Yuan, Gerald Schaefer, Shihua Zhou, George Vogiatzis, Yifan Wang and Hui Fang. “A dual-aligned knowledge self-distillation framework for visible-infrared cross-modal person re-identification.” Knowledge-Based Systems, 330, pp. 114525. 2025.

@article{deng2025,
  title     = {A dual-aligned knowledge self-distillation framework for visible-infrared cross-modal person re-identification},
  author    = {Siyuan Deng and Kunhao Yuan and Gerald Schaefer and Shihua Zhou and George Vogiatzis and Yifan Wang and Hui Fang},
  journal   = {Knowledge-Based Systems},
  volume    = {330},
  pages     = {114525},
  year      = {2025},
  doi       = {10.1016/j.knosys.2025.114525},
}