arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.09504cs.CV
收藏

HydraMix:面向小数据图像分类的多图像特征混合

HydraMix: Multi-Image Feature Mixing for Small Data Image Classification

Institute for Information Processing / L3S, Leibniz University Hannover(汉诺威莱布尼茨大学信息处理研究所 / L3S)

Christoph Reinders, Frederik Schubert, Bodo Rosenhahn

AI总结:

提出 HydraMix 架构,通过分割掩码在特征空间融合同类多图像,并结合无监督与对抗训练实现小数据增强,在多个基准上提升分类性能。

摘要:

训练深度神经网络需要包含大量带标注样本的数据集。收集和标注这些数据集不仅极其昂贵,而且面临法律和隐私问题。这些因素对许多现实应用构成了显著限制。为解决这一问题,我们提出 HydraMix,这是一种新颖架构,通过混合来自同一类别的多张不同图像来生成新的图像合成结果。HydraMix 在特征空间中学习由基于分割的混合掩码引导的多张图像内容融合,并通过无监督训练与对抗训练相结合的方式进行优化。我们的数据增强方案支持在非常小的数据集上从头训练模型。我们在 ciFAIR-10、STL-10 和 ciFAIR-100 上进行了大量实验。此外,我们提出了一种新颖的文本-图像度量,用于评估增强数据集的通用性。结果表明,在小数据集图像分类任务上,HydraMix 优于现有最先进方法。

英文摘要:

Training deep neural networks requires datasets with a large number of annotated examples. The collection and annotation of these datasets is not only extremely expensive but also faces legal and privacy problems. These factors are a significant limitation for many real-world applications. To address this, we introduce HydraMix, a novel architecture that generates new image compositions by mixing multiple different images from the same class. HydraMix learns the fusion of the content of various images guided by a segmentation-based mixing mask in feature space and is optimized via a combination of unsupervised and adversarial training. Our data augmentation scheme allows the creation of models trained from scratch on very small datasets. We conduct extensive experiments on ciFAIR-10, STL-10, and ciFAIR-100. Additionally, we introduce a novel text-image metric to assess the generality of the augmented datasets. Our results show that HydraMix outperforms existing state-of-the-art methods for image classification on small datasets.

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。

↑