Free Lunch for Gait Recognition: A Novel Relation Descriptor

TL;DR

This paper introduces a relation descriptor for gait recognition that captures both individual features and relationships with gait anchors, improving robustness and accuracy without extra computational costs.

Contribution

The paper proposes a novel relation descriptor that reinterprets classifier weights as gait anchors, enhancing gait recognition by leveraging inter-personal relationships.

Findings

Outperforms baseline methods on multiple datasets

Achieves state-of-the-art accuracy in gait recognition

Effectively leverages classifier weights as gait anchors

Abstract

Gait recognition is to seek correct matches for query individuals by their unique walking patterns. However, current methods focus solely on extracting individual-specific features, overlooking ``interpersonal" relationships. In this paper, we propose a novel $\textbf{Relation Descriptor}$ that captures not only individual features but also relations between test gaits and pre-selected gait anchors. Specifically, we reinterpret classifier weights as gait anchors and compute similarity scores between test features and these anchors, which re-expresses individual gait features into a similarity relation distribution. In essence, the relation descriptor offers a holistic perspective that leverages the collective knowledge stored within the classifier's weights, emphasizing meaningful patterns and enhancing robustness. Despite its potential, relation descriptor poses dimensionality challenges since its dimension depends on the training set's identity count. To address this, we propose Farthest gait-Anchor Selection to identify the most discriminative gait anchors and an Orthogonal Regularization Loss to increase diversity within gait anchors. Compared to individual-specific features extracted from the backbone, our relation descriptor can boost the performance nearly without any extra costs. We evaluate the effectiveness of our method on the popular GREW, Gait3D, OU-MVLP, CASIA-B, and CCPG, showing that our method consistently outperforms the baselines and achieves state-of-the-art performance.