Spectrum-guided Feature Enhancement Network for Event Person Re-Identification

TL;DR

This paper introduces SFE-Net, a novel network for event-based person re-identification that uses spectrum attention and patch dropout to improve noise filtering and feature robustness, achieving state-of-the-art results.

Contribution

The paper proposes SFE-Net with MSAM and CPDM components, innovatively applying Fourier spectrum filtering and patch dropout for enhanced event Re-ID performance.

Findings

SFE-Net outperforms existing methods on event Re-ID datasets.

MSAM effectively filters event noise and captures discriminative features.

CPDM encourages the model to focus on all body regions for robust descriptors.

Abstract

As a cutting-edge biosensor, the event camera holds significant potential in the field of computer vision, particularly regarding privacy preservation. However, compared to traditional cameras, event streams often contain noise and possess extremely sparse semantics, posing a formidable challenge for event-based person re-identification (event Re-ID). To address this, we introduce a novel event person re-identification network: the Spectrum-guided Feature Enhancement Network (SFE-Net). This network consists of two innovative components: the Multi-grain Spectrum Attention Mechanism (MSAM) and the Consecutive Patch Dropout Module (CPDM). MSAM employs a fourier spectrum transform strategy to filter event noise, while also utilizing an event-guided multi-granularity attention strategy to enhance and capture discriminative person semantics. CPDM employs a consecutive patch dropout strategy to generate multiple incomplete feature maps, encouraging the deep Re-ID model to equally perceive each effective region of the person's body and capture robust person descriptors. Extensive experiments on Event Re-ID datasets demonstrate that our SFE-Net achieves the best performance in this task.