GaitKD: A Universal Decoupled Distillation Framework for Efficient Gait Recognition
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918472997404672 |
|---|---|
| author | Li, Yuqi Zhou, Qian Duan, Huiran Wang, Jingjie Zhang, Shunli Yang, Chuanguang Zhao, Guoying Tian, Yingli |
| author_facet | Li, Yuqi Zhou, Qian Duan, Huiran Wang, Jingjie Zhang, Shunli Yang, Chuanguang Zhao, Guoying Tian, Yingli |
| contents | Gait recognition is an attractive biometric modality for long-range and contact-free identification, but high-performing gait models often rely on deep and computationally expensive architectures that are difficult to deploy in practice. Knowledge distillation (KD) offers a natural way to transfer knowledge from a powerful teacher to an efficient student; however, standard KD is often less effective for part-structured gait models, where supervision is formed from both part-wise classification logits and part-wise retrieval embeddings. In this paper, we propose GaitKD, a distillation framework that decouples gait knowledge transfer into two complementary components: decision-level distillation and boundary-level distillation. Specifically, GaitKD aligns the teacher and student through part-calibrated logit distillation to transfer inter-class decision relations, while preserving the teacher-induced partitioning of the embedding space through an activation-boundary objective instead of direct feature regression. With a simple aligned part-wise design, GaitKD supports heterogeneous teacher-student gait models without introducing additional inference cost. Experimental results across multiple gait recognition benchmarks and teacher-student configurations show consistent improvements over strong gait baselines. Our study demonstrates that the two transfer components are complementary, and boundary-preserving distillation provides more stable performance than direct feature regression. Source code is available at https://github.com/liyiersan/GaitKD/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_26255 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GaitKD: A Universal Decoupled Distillation Framework for Efficient Gait Recognition Li, Yuqi Zhou, Qian Duan, Huiran Wang, Jingjie Zhang, Shunli Yang, Chuanguang Zhao, Guoying Tian, Yingli Computer Vision and Pattern Recognition Gait recognition is an attractive biometric modality for long-range and contact-free identification, but high-performing gait models often rely on deep and computationally expensive architectures that are difficult to deploy in practice. Knowledge distillation (KD) offers a natural way to transfer knowledge from a powerful teacher to an efficient student; however, standard KD is often less effective for part-structured gait models, where supervision is formed from both part-wise classification logits and part-wise retrieval embeddings. In this paper, we propose GaitKD, a distillation framework that decouples gait knowledge transfer into two complementary components: decision-level distillation and boundary-level distillation. Specifically, GaitKD aligns the teacher and student through part-calibrated logit distillation to transfer inter-class decision relations, while preserving the teacher-induced partitioning of the embedding space through an activation-boundary objective instead of direct feature regression. With a simple aligned part-wise design, GaitKD supports heterogeneous teacher-student gait models without introducing additional inference cost. Experimental results across multiple gait recognition benchmarks and teacher-student configurations show consistent improvements over strong gait baselines. Our study demonstrates that the two transfer components are complementary, and boundary-preserving distillation provides more stable performance than direct feature regression. Source code is available at https://github.com/liyiersan/GaitKD/ |
| title | GaitKD: A Universal Decoupled Distillation Framework for Efficient Gait Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.26255 |