相位信息对小样本细粒度图像分类的影响
Phase-Aware Spatial-Frequency Fusion for Few-Shot Fine-Grained Image Classification
AI总结：
针对小样本细粒度图像分类任务，研究人员提出幅相集成（API）模块与PSF-Net网络，通过融合相位信息提升特征质量，在五个公开数据集上实现优于现有SOTA的性能。
AI中文摘要：
小样本细粒度图像分类（FSFGIC）旨在利用有限的标注示例对相似图像进行分类。本研究强调了相位信息在捕捉图像内部结构关系方面的关键作用，而该作用此前未被充分利用。研究提出了一种新颖的即插即用式幅相集成（API）模块，该模块可有效结合局部与全局频率幅度及相位信息，以获取更全面的特征描述子。此外，还提出了名为PSF-Net的专用网络，该网络可自适应融合基于相位的空间与频率信息，用于FSFGIC。所设计的PSF-Net可轻松集成至标准的 episode 训练架构中，实现从零开始的端到端训练。在五个公开数据集上开展的大量实验表明，该方法的性能优于现有最先进的基准模型。
英文摘要：
Few-shot fine-grained image classification (FSFGIC) aims to classify similar images with limited labeled examples. This work highlights the critical yet underutilized role of phase information in capturing structural relationships within an image. This study introduces a novel plug-and-play amplitude-phase integration (API) module that effectively combines local and global frequency amplitude and phase information for obtaining more comprehensive feature descriptors. Additionally, a dedicated network, named PSF-Net, is proposed that adaptively fuses phase-based spatial and frequency information for FSFGIS. The designed PSF-Net can be easily integrated into standard episodic training architectures for end-to-end training from scratch. Extensive experiments on five public datasets demonstrate that the method outperforms existing state-of-the-art benchmarks.
