GaitKD: A Universal Decoupled Distillation Framework for Efficient Gait Recognition

TL;DR

GaitKD is a novel decoupled knowledge distillation framework that enhances gait recognition models by separately transferring decision relations and embedding boundaries, achieving efficiency and improved accuracy.

Contribution

It introduces a decoupled distillation approach for gait recognition that supports heterogeneous models without extra inference cost.

Findings

GaitKD improves performance across multiple benchmarks.

Boundary-preserving distillation outperforms direct feature regression.

The framework supports heterogeneous teacher-student configurations.

Abstract

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/