Large vision models (LVM) based gait recognition has achieved impressive performance. However, existing LVM-based approaches may overemphasize gait priors while neglecting the intrinsic value of LVM itself, particularly the rich, distinct representations across its multi-layers. To adequately unlock LVM's potential, this work investigates the impact of layer-wise representations on downstream recognition tasks. Our analysis reveals that LVM's intermediate layers offer complementary properties across tasks, integrating them yields an impressive improvement even without rich well-designed gait priors. Building on this insight, we propose a simple and universal baseline for LVM-based gait recognition, termed BiggerGait. Comprehensive evaluations on CCPG, CAISA-B*, SUSTech1K, and CCGR\_MINI validate the superiority of BiggerGait across both within- and cross-domain tasks, establishing it as a simple yet practical baseline for gait representation learning. All the models and code will be publicly available.
View on arXiv@article{ye2025_2505.18132,
title={ BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models },
author={ Dingqiang Ye and Chao Fan and Zhanbo Huang and Chengwen Luo and Jianqiang Li and Shiqi Yu and Xiaoming Liu },
journal={arXiv preprint arXiv:2505.18132},
year={ 2025 }
}