针对红外目标检测，通过分离高低频特征实现更精准的跨模态知识迁移。
FreqKD: Frequency-Decoupled Cross-Modal Knowledge Distillation for Infrared Object Detection
- 按空间频率解耦蒸馏：低频用均方误差保结构，高频用松弛对数均方误差容纹理差异。
- 在KAIST数据集上提升2.4点mAP50，高频频段差异是低频的2.4倍。
- 可跨数据集、任务和模型架构迁移，适合红外感知与多模态学习研究者。
通过知识蒸馏将大规模RGB基础模型迁移到红外图像仍具挑战，源于成像物理的根本差异。我们分析了RGB-IR模态差距的频谱结构，发现特征发散在不同空间频率上不均等：低频成分（形状、布局）比高频成分（纹理、细边缘）具有更强的跨模态一致性，后者反映模态特异性。基于此，提出频域解耦蒸馏框架FreqKD，对各频带采用异构监督策略。在低频带施加严格的均方误差（MSE）以保留共享结构信息，在高频带采用松弛的对数均方误差（加权0.1）提供边缘引导的同时容忍纹理差异。500对样本的频谱发散分析显示，所有分析的Transformer层中，高频发散平均高出低频2.4倍。在KAIST多光谱行人检测上，FreqKD达到64.1 mAP50，较DINOv2基线提升2.4点。所学表征可在其他数据集（FLIR ADAS，+2.1 mAP50）、任务（MFNet分割，+1.85 mIoU）和架构（ResNet-50，+1.0 mAP50）上有效迁移。代码已公开。
原文摘要 · Abstract (English)
Transfer learning from large-scale RGB foundation models to infrared (IR) imagery through knowledge distillation (KD) remains challenging due to fundamental differences in image formation physics. We investigate the spectral structure of the RGB--IR modality gap and observe that feature divergence is not uniform across spatial frequencies: low-frequency components (shape, layout) show greater cross-modal alignment than high-frequency components (texture, fine edges), which reflect modality-specific characteristics. Based on this analysis, we propose FreqKD, a frequency-decoupled distillation framework that applies asymmetric supervision adapted to each band's cross-modal consistency. The method employs strict mean squared error (MSE) on the low-frequency band to preserve shared structural information and a relaxed log-MSE loss (weighted at 0.1) on the high-frequency band to provide edge guidance while tolerating texture differences. Spectral divergence analysis on 500 paired samples shows that high-frequency divergence exceeds low-frequency divergence by a factor of 2.4x on average across all analysed transformer layers. On KAIST multispectral pedestrian detection, FreqKD achieves 64.1 mAP50, improving 2.4 points over the DINOv2 baseline. The learned representation transfers across datasets (FLIR ADAS, +2.1 mAP50), tasks (MFNet segmentation, +1.85 mean intersection-over-union), and architectures (ResNet-50, +1.0 mAP50). Code is available at: https://anonymous.4open.science/r/freq_decoupled_kd-5E5A
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。