从少路到多路：重新审视少样本细粒度图像分类
From Few-way to Many-way: Rethinking Few-shot Fine-grained Image Classification
论文指出情节式训练在 many-way 场景下缺乏对特征空间的全局刻画，提出自特征与协同特征提取加情节级与全局级双重优化的思路，可直接迁移到其他少样本/小样本识别任务中改进特征空间结构。
原文依据 existing approaches lack a reliable and global characterization of the feature space
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论少样本细粒度图像分类（FSFG）旨在仅凭少量带标签样本识别新的细粒度类别。现有 FSFG 方法主要关注细粒度特征提取，并在包含少量类别的训练情节内建模查询与支持集之间的交互。依托情节式训练策略，这些方法通常假设在训练样本上学到的能力可以直接迁移到包含少量新类别（少路）的评估情节中。然而，在涉及大量新类别（多路）的更实际、更具挑战性的场景下，现有方法缺乏对特征空间可靠且全局的刻画，使得仅靠情节式自适应难以有效泛化。本文首次对 FSFG 中新类别的行为进行理论分析，并推导出类别判别性指数的界。在该分析的指导下，我们提出一种新的 SCEG 方法，融合自特征与协同特征提取，以及情节级与全局级的特征空间优化。大量实验表明，我们的方法在传统少路设置与新的多路设置下均持续且显著优于现有方法。代码见：https://github.com/Legenddddd/SCEG。
英文原文摘要 1304 字符
Few-shot fine-grained image classification (FSFG) aims to recognize novel fine-grained categories from only a few labeled samples. Existing FSFG methods primarily focus on fine-grained feature extraction and modeling query-support interactions within training episodes containing a small number of classes. Relying on the episodic training strategy, these methods typically assume that the capabilities learned on training samples can directly transfer to evaluation episodes with a few novel classes (few-way). However, in more practical and challenging scenarios involving many novel classes (many-way), existing approaches lack a reliable and global characterization of the feature space, making it difficult for episodic adaptation alone to generalize effectively. In this paper, we pioneer a theoretical analysis of novel class behavior in FSFG and derive a class discriminative index bound. Guided by this analysis, we propose a novel SCEG method that incorporates Self and Collaborative feature extraction as well as Episodic and Global feature space optimization. Extensive experiments demonstrate that our method consistently and significantly outperforms existing methods under both conventional few-way and the new many-way settings. Codes are available at: https://github.com/Legenddddd/SCEG.