Collaborative Enhancement Network for Low-quality Multi-spectral Vehicle Re-identification

2025-04-21

AI Summary

Multispectral vehicle re-identification suffers significant performance degradation when visible, near-infrared, and thermal infrared modalities exhibit heterogeneous quality, primarily due to missing discriminative cues. Existing methods rely on a single high-quality “primary spectrum” for cross-modal enhancement, yet the optimal primary spectrum is difficult to determine a priori and such enhancement fails when its quality degrades. This paper proposes the Collaborative Enhancement Network (CoEN). First, we introduce a novel proxy-driven Dynamic Quality Sorting Mechanism (DQSM) that generates high-fidelity multispectral proxy features via a Proxy Generator to adaptively rank and select the optimal primary spectrum. Second, we design a Collaborative Enhancement Module (CEM) enabling bidirectional complementary feature enhancement across all spectra. Unlike prior unidirectional paradigms dependent on a fixed high-quality primary spectrum, CoEN achieves robust, adaptive enhancement. It sets new state-of-the-art results on three benchmarks and maintains stable performance gains even under primary-spectrum degradation. Code is publicly available.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Security and Privacy: Privacy-enhancing technologies

Abstract

The performance of multi-spectral vehicle Re-identification (ReID) is significantly degraded when some important discriminative cues in visible, near infrared and thermal infrared spectra are lost. Existing methods generate or enhance missing details in low-quality spectra data using the high-quality one, generally called the primary spectrum, but how to justify the primary spectrum is a challenging problem. In addition, when the quality of the primary spectrum is low, the enhancement effect would be greatly degraded, thus limiting the performance of multi-spectral vehicle ReID. To address these problems, we propose the Collaborative Enhancement Network (CoEN), which generates a high-quality proxy from all spectra data and leverages it to supervise the selection of primary spectrum and enhance all spectra features in a collaborative manner, for robust multi-spectral vehicle ReID. First, to integrate the rich cues from all spectra data, we design the Proxy Generator (PG) to progressively aggregate multi-spectral features. Second, we design the Dynamic Quality Sort Module (DQSM), which sorts all spectra data by measuring their correlations with the proxy, to accurately select the primary spectra with the highest correlation. Finally, we design the Collaborative Enhancement Module (CEM) to effectively compensate for missing contents of all spectra by collaborating the primary spectra and the proxy, thereby mitigating the impact of low-quality primary spectra. Extensive experiments on three benchmark datasets are conducted to validate the efficacy of the proposed approach against other multi-spectral vehicle ReID methods. The codes will be released at https://github.com/yongqisun/CoEN.

Problem

• Degraded performance in multi-spectral vehicle ReID due to lost discriminative cues
• Challenges in justifying and selecting primary spectrum for data enhancement
• Limited enhancement effect when primary spectrum quality is low

Innovation

• Generates high-quality proxy from all spectra data
• Dynamically selects primary spectrum using proxy correlation
• Collaboratively enhances all spectra features with proxy