BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models

Xiaoming Liu (Michigan State University) · Dingqiang Ye (Southern University of Science and Technology) · Chao Fan (Shenzhen University) · Zhanbo Huang (Michigan State University) · Chengwen Luo (Shenzhen University) · Jianqiang Li (Shenzhen University) · Shiqi Yu (Southern University of Science and Technology)
baseline methodsbiggergaitcomplementary propertiescross-domain tasksdownstream recognition tasksgait priorsgait recognitionintegrationintermediate layerslarge vision modelslayer-wise representationsmodel architectureperformance evaluationrepresentation learningtask-specific improvements

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 are available at https://github.com/ShiqiYu/OpenGait/.