CLASH: Complementary Learning with Neural Architecture Search for Gait Recognition

TL;DR

This paper introduces CLASH, a framework combining dense spatial-temporal gait descriptors with neural architecture search to improve gait recognition accuracy, especially in challenging real-world scenarios.

Contribution

The paper proposes a novel dense spatial-temporal field descriptor and a task-specific neural architecture search method for enhanced gait recognition.

Findings

Achieves 98.8% rank-1 accuracy on CASIA-B under normal conditions.

Outperforms state-of-the-art silhouette methods by 16.3% on Gait3D.

Effective in both lab and wild scenarios.

Abstract

Gait recognition, which aims at identifying individuals by their walking patterns, has achieved great success based on silhouette. The binary silhouette sequence encodes the walking pattern within the sparse boundary representation. Therefore, most pixels in the silhouette are under-sensitive to the walking pattern since the sparse boundary lacks dense spatial-temporal information, which is suitable to be represented with dense texture. To enhance the sensitivity to the walking pattern while maintaining the robustness of recognition, we present a Complementary Learning with neural Architecture Search (CLASH) framework, consisting of walking pattern sensitive gait descriptor named dense spatial-temporal field (DSTF) and neural architecture search based complementary learning (NCL). Specifically, DSTF transforms the representation from the sparse binary boundary into the dense distance-based texture, which is sensitive to the walking pattern at the pixel level. Further, NCL presents a task-specific search space for complementary learning, which mutually complements the sensitivity of DSTF and the robustness of the silhouette to represent the walking pattern effectively. Extensive experiments demonstrate the effectiveness of the proposed methods under both in-the-lab and in-the-wild scenarios. On CASIA-B, we achieve rank-1 accuracy of 98.8%, 96.5%, and 89.3% under three conditions. On OU-MVLP, we achieve rank-1 accuracy of 91.9%. Under the latest in-the-wild datasets, we outperform the latest silhouette-based methods by 16.3% and 19.7% on Gait3D and GREW, respectively.