Database-Agnostic Gait Enrollment using SetTransformers

TL;DR

This paper presents a dataset-agnostic, transformer-based framework for open-set gait enrollment that effectively determines whether a gait sample belongs to a known individual or is new, without retraining for different environments.

Contribution

Introduces a novel SetTransformer-based method for open-set gait enrollment that is dataset-agnostic and compatible with various recognition architectures, enhancing scalability and flexibility.

Findings

Effective enrollment across different datasets and scenarios

Scales better with data compared to traditional methods

Compatible with multiple gait recognition models

Abstract

Gait recognition has emerged as a powerful tool for unobtrusive and long-range identity analysis, with growing relevance in surveillance and monitoring applications. Although recent advances in deep learning and large-scale datasets have enabled highly accurate recognition under closed-set conditions, real-world deployment demands open-set gait enrollment, which means determining whether a new gait sample corresponds to a known identity or represents a previously unseen individual. In this work, we introduce a transformer-based framework for open-set gait enrollment that is both dataset-agnostic and recognition-architecture-agnostic. Our method leverages a SetTransformer to make enrollment decisions based on the embedding of a probe sample and a context set drawn from the gallery, without requiring task-specific thresholds or retraining for new environments. By decoupling enrollment from the main recognition pipeline, our model is generalized across different datasets, gallery sizes, and identity distributions. We propose an evaluation protocol that uses existing datasets in different ratios of identities and walks per identity. We instantiate our method using skeleton-based gait representations and evaluate it on two benchmark datasets (CASIA-B and PsyMo), using embeddings from three state-of-the-art recognition models (GaitGraph, GaitFormer, and GaitPT). We show that our method is flexible, is able to accurately perform enrollment in different scenarios, and scales better with data compared to traditional approaches. We will make the code and dataset scenarios publicly available.