跨域少样本学习中的大间隔机制与伪查询集
Large Margin Mechanism and Pseudo Query Set on Cross-Domain Few-Shot Learning
AI总结：
针对跨域少样本学习，提出大间隔微调方法LMM-PQS，通过生成伪查询图像并采用大间隔机制，显著提升模型在多个新领域的适应能力。
摘要：
近年来，少样本学习问题受到了广泛关注。以往大多数工作的方法都是在单一领域的数据集上进行训练和测试，而跨域少样本学习是少样本学习问题的一个全新分支，其中模型在训练和测试阶段处理不同领域的数据集。本文针对模型在单一数据集上预训练（元训练）而在四个不同领域（包括常见物体、卫星图像和医学图像）的数据集上进行微调的问题，提出了一种新颖的大间隔微调方法（LMM-PQS），该方法从支持图像生成伪查询图像，并借鉴人脸识别方法中的大间隔机制对特征提取模块进行微调。实验结果表明，LMM-PQS显著超越了基线模型，证明了我们的方法具有鲁棒性，能够轻松地将预训练模型适应到数据稀少的新领域。
英文摘要：
In recent years, few-shot learning problems have received a lot of attention. While methods in most previous works were trained and tested on datasets in one single domain, cross-domain few-shot learning is a brand-new branch of few-shot learning problems, where models handle datasets in different domains between training and testing phases. In this paper, to solve the problem that the model is pre-trained (meta-trained) on a single dataset while fine-tuned on datasets in four different domains, including common objects, satellite images, and medical images, we propose a novel large margin fine-tuning method (LMM-PQS), which generates pseudo query images from support images and fine-tunes the feature extraction modules with a large margin mechanism inspired by methods in face recognition. According to the experiment results, LMM-PQS surpasses the baseline models by a significant margin and demonstrates that our approach is robust and can easily adapt pre-trained models to new domains with few data.
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。
