MFEN：面向可见光-红外行人重识别的多频专家网络
MFEN: Multi-Frequency Expert Network for Visible-Infrared Person Re-ID
把频域分带调制与混合专家结合，用于抑制光照/波长差异带来的模态鸿沟；做跨模态检索或可见光-红外对齐时，可复用其多频带专家路由与随机频率增强策略。
原文依据 we propose a Multi-Frequency Expert Network (MFEN) that enables multi-frequency modulation and adaptively combines different bands through a mixture-of-experts design
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论可见光-红外行人重识别（VI-ReID）因可见光与红外图像之间存在较大的模态差异而具有挑战性。我们认为，这种差异在很大程度上与光照条件的不同有关，包括光波长和光源类型的差异。近期，基于频率的 VI-ReID 方法取得了显著成效，因为频率信息能够更好地提取与身份相关的轮廓和细节，同时排除无关的光照与颜色信息。然而，现有方法要么不区分不同频带，要么只关注单一频带，在多样化的光照条件下显得不足。为进行全面的频域学习，我们提出多频专家网络（MFEN），通过混合专家设计实现多频调制并自适应地组合不同频带。我们进一步引入随机频率增强（RFA）与频率辅助优化（FAO）以更好地训练 MFEN。三个模块相互补充，共同捕捉关键的频域细节以实现鲁棒的表征学习。在三个 VI-ReID 数据集上的大量实验验证了本方法的有效性。
英文原文摘要 1227 字符
Visible-infrared person re-identification (VI-ReID) is challenging due to the large modality discrepancy between visible and infrared images. We contend that this discrepancy is largely related to differing lighting conditions, including differences in light wavelength and light source type. Recently, frequency-based VI-ReID approaches have achieved notable success because frequency information can better extract identity-relevant contours and details while excluding irrelevant lighting and color. However, existing methods either do not distinguish different frequency bands or focus on only one band, which is insufficient under diverse lighting conditions. To perform comprehensive frequency-domain learning, we propose a Multi-Frequency Expert Network (MFEN) that enables multi-frequency modulation and adaptively combines different bands through a mixture-of-experts design. We further introduce Random Frequency Augmentation (RFA) and Frequency Auxiliary Optimization (FAO) to better train MFEN. The three modules are complementary and jointly capture critical frequency-domain details for robust representation learning. Extensive experiments on three VI-ReID datasets demonstrate the effectiveness of our approach.