Gait Recognition via Collaborating Discriminative and Generative Diffusion Models

TL;DR

This paper introduces CoD$^2$, a novel gait recognition framework that combines diffusion-based generative models with discriminative models, enhancing feature robustness and achieving state-of-the-art results across multiple datasets.

Contribution

The paper presents a new framework integrating diffusion models with discriminative features using multi-level conditional control for improved gait recognition.

Findings

Achieves state-of-the-art performance on four gait datasets.

Seamlessly integrates with existing discriminative methods for enhanced accuracy.

Demonstrates the effectiveness of combining generative and discriminative models in gait recognition.

Abstract

Gait recognition offers a non-intrusive biometric solution by identifying individuals through their walking patterns. Although discriminative models have achieved notable success in this domain, the full potential of generative models remains largely underexplored. In this paper, we introduce \textbf{CoD$^2$}, a novel framework that combines the data distribution modeling capabilities of diffusion models with the semantic representation learning strengths of discriminative models to extract robust gait features. We propose a Multi-level Conditional Control strategy that incorporates both high-level identity-aware semantic conditions and low-level visual details. Specifically, the high-level condition, extracted by the discriminative extractor, guides the generation of identity-consistent gait sequences, whereas low-level visual details, such as appearance and motion, are preserved to enhance consistency. Furthermore, the generated sequences facilitate the discriminative extractor's learning, enabling it to capture more comprehensive high-level semantic features. Extensive experiments on four datasets (SUSTech1K, CCPG, GREW, and Gait3D) demonstrate that CoD$^2$ achieves state-of-the-art performance and can be seamlessly integrated with existing discriminative methods, yielding consistent improvements.