仅用一张图生成多样化增强图像，提升少样本分类准确率
1S-DAug: One-Shot Data Augmentation for Robust Few-Shot Generalization
- 基于单张图像生成多样且真实的增强图像，结合几何变换与去噪扩散
- 在miniImageNet上实现最高20%的相对准确率提升，跨4个数据集稳定增益
- 无需训练、兼容任意模型，适合部署于少样本场景的快速优化
少样本学习（FSL）要求模型仅凭少量标注样本即可泛化到新类别，传统测试时增强在此场景下效果不佳。本文提出1S-DAug，一种仅需一个样本即可在测试时生成多样化且忠实的增强图像的生成式增强方法。该方法结合传统几何扰动、可控噪声注入以及以原图条件化的去噪扩散过程，生成图像经编码聚合后与原始图像共同构成增强表示，用于更鲁棒的少样本预测。作为无训练、模型无关的插件，1S-DAug在4个不同数据集的标准基准上均显著提升少样本分类性能，尤其在miniImageNet 5-way-1-shot任务上达到最高20%的相对准确率提升。此外，还扩展至更大视觉语言模型并进行理论分析。
原文摘要 · Abstract (English)
Few-shot learning (FSL) challenges model generalization to novel classes based on just a few shots of labeled examples, a testbed where traditional test-time augmentations fail to be effective. We introduce 1S-DAug, a one-shot generative augmentation operator that synthesizes diverse yet faithful variants from just one example image at test time. 1S-DAug couples traditional geometric perturbations with controlled noise injection and a denoising diffusion process conditioned on the original image. The generated images are then encoded and aggregated, alongside the original image, into a combined representation for more robust few-shot predictions. Integrated as a training-free model-agnostic plugin, 1S-DAug consistently improves few-shot classification across standard benchmarks of 4 different datasets without any model parameter update, including achieving up to 20\% relative accuracy improvement on the miniImagenet 5-way-1-shot benchmark. Additionally, we provide extension experiments on the larger vision language models as well as theoretical analyses.
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。