基于大型语言模型类实体推理的少样本学习设想
Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning
AI总结：
针对少样本学习中抽象类名无法捕捉细粒度特征的问题，提出结合大型语言模型提取的抽象类语义与具体类实体的新框架，通过SVPE和PC模块优化类原型，在多个基准上取得显著提升。
摘要：
少样本学习（FSL）旨在利用有限数量的视觉样本来识别新概念。现有方法试图将语义信息融入有限的视觉数据中以进行类别理解。然而，这些方法通常使用抽象的类别名称来丰富类级特征表示，未能捕捉到有效泛化所必需的细微特征。为了解决这个问题，我们提出了一种新的FSL框架，该框架结合了从大型语言模型（LLMs）中提取的抽象类语义和具体类实体，以增强类原型的表示。具体来说，我们的框架由语义引导的视觉模式提取（SVPE）模块和原型校准（PC）模块组成，其中SVPE跨多个尺度精细地提取语义感知的视觉模式，而PC模块无缝集成这些模式以细化视觉原型，增强其代表性。在四个少样本分类基准和 BSCD-FSL 跨域基准上的大量实验展示了相对于当前最先进方法的显著进步。值得注意的是，对于具有挑战性的单样本设置，我们的方法使用 ResNet-12 主干网络，取得了比次优竞争者平均1.95%的令人印象深刻的改进。
英文摘要：
Few-shot learning (FSL) aims to recognize new concepts using a limited number of visual samples. Existing approaches attempt to incorporate semantic information into the limited visual data for category understanding. However, these methods often enrich class-level feature representations with abstract category names, failing to capture the nuanced features essential for effective generalization. To address this issue, we propose a novel framework for FSL, which incorporates both the abstract class semantics and the concrete class entities extracted from Large Language Models (LLMs), to enhance the representation of the class prototypes. Specifically, our framework composes a Semantic-guided Visual Pattern Extraction (SVPE) module and a Prototype-Calibration (PC) module, where the SVPE meticulously extracts semantic-aware visual patterns across diverse scales, while the PC module seamlessly integrates these patterns to refine the visual prototype, enhancing its representativeness. Extensive experiments on four few-shot classification benchmarks and the BSCD-FSL cross-domain benchmarks showcase remarkable advancements over the current state-of-the-art methods. Notably, for the challenging one-shot setting, our approach, utilizing the ResNet-12 backbone, achieves an impressive average improvement of 1.95% over the second-best competitor.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
