BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models
This work addresses gait recognition for biometric identification, offering an incremental improvement by better utilizing existing large vision models.
The paper tackled the problem of gait recognition by investigating the impact of layer-wise representations from large vision models, revealing that integrating intermediate layers yields significant improvements without relying heavily on gait priors. The proposed BiggerGait method achieved superior performance on multiple datasets, establishing it as a practical baseline for gait representation learning.
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.