FracMix: A Fractional Fourier Based Augmentation for Generalizable Person Re-Identification
IEEE Signal Processing Letters · 2026 · 33 · 2126-2130
DOI: 10.1109/lsp.2026.3689372 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Jieru Jia und 6 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Program of Shanxi Province, Shanxi Scholarship Council of China.
Abstract (Originalsprache)
Domain generalization in person re-identification (DG re-ID) aims to build models that can accurately retrieve a targeted person across cameras in arbitrary unseen domains, without access to those domains during training. Data augmentation (DA) has become a de facto solution to DG re-ID, and one line of approaches realizes this goal from a frequency-centric perspective, where the Fourier Transform (FT) is employed to mix amplitudes for novel sample generation. However, FT-based strategies are fundamentally limited by the assumption of signal stationarity, which may be inadequate to explore a broader perturbation space. To overcome this limitation, this work investigates the potential of the Fractional Fourier Transform (FrFT) for DA and proposes FracMix (Fractional Fourier based MixUp), which yields an intermediate representation that bridges spatial and frequency domains with a fractional order $\alpha$ , enabling the generation of richer samples. Furthermore, an Adaptive Token Pruning strategy (ATP) is designed to dynamically select the top- $K$ salient tokens and perform perturbations exclusively to corresponding patches. This simple yet effective mechanism alleviates over-reliance on a small set of dominant patches and encourages broader contextual utilization, thereby improving robustness and generalization. Experiments on multiple DG re-ID benchmarks demonstrate the effectiveness of FracMix.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Program of Shanxi Province
- Shanxi Scholarship Council of China
- Postgraduate Education Innovation Program of Shanxi Province
Zitieren
APA
Jia, J., Xie, H., Qian, Y., Song, Y., Yan, T., Zhang, L., & Li, C. (2026). FracMix: A Fractional Fourier Based Augmentation for Generalizable Person Re-Identification. IEEE Signal Processing Letters, 33, 2126-2130. https://doi.org/10.1109/lsp.2026.3689372
Vancouver
Jia J, Xie H, Qian Y, Song Y, Yan T, Zhang L, et al. FracMix: A Fractional Fourier Based Augmentation for Generalizable Person Re-Identification. IEEE Signal Processing Letters. 2026;33:2126-2130. doi:10.1109/lsp.2026.3689372
BibTeX
@article{Jia2026,
author = {Jia, Jieru and Xie, Huidi and Qian, Yuhua and Song, Yantao and Yan, Tao and Zhang, Lichao and Li, Chao},
title = {FracMix: A Fractional Fourier Based Augmentation for Generalizable Person Re-Identification},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {2126--2130},
doi = {10.1109/lsp.2026.3689372}
}
EUVIMED