arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.07944cs.CVcs.AI
收藏

利用扩散模型实现有效的数据增强

Effective Data Augmentation With Diffusion Models

Carnegie Mellon University(卡内基梅隆大学);MPG Ranch(MPG牧场);University Of Chicago(芝加哥大学);Laboratory Schools(实验室学校)

Brandon Trabucco, Kyle Doherty, Max Gurinas, Ruslan Salakhutdinov

AI总结:

针对传统数据增强语义多样性不足的问题,提出利用预训练文本到图像扩散模型进行图像编辑的增强方法,仅需少量标注即可泛化新概念,在少样本分类和杂草识别任务中提升了准确率。

摘要:

数据增强是深度学习中最常用的工具之一,支撑了近年来包括分类、生成模型和表示学习在内的诸多进展。标准的数据增强方法结合旋转、翻转等简单变换,从现有图像生成新图像。然而,这些新图像在数据中存在的关键语义维度上缺乏多样性。当前的增强方法无法改变高层语义属性(例如场景中出现的动物物种)来提升数据多样性。我们通过由预训练文本到图像扩散模型参数化的图像到图像变换,解决数据增强中多样性不足的问题。我们的方法使用现成的扩散模型编辑图像以改变其语义,并且仅需少量标注样本就能泛化到新的视觉概念。我们在少样本图像分类任务以及真实世界的杂草识别任务上评估了该方法,发现在测试领域中准确率有所提升。

英文摘要:

Data augmentation is one of the most prevalent tools in deep learning, underpinning many recent advances, including those from classification, generative models, and representation learning. The standard approach to data augmentation combines simple transformations like rotations and flips to generate new images from existing ones. However, these new images lack diversity along key semantic axes present in the data. Current augmentations cannot alter the high-level semantic attributes, such as animal species present in a scene, to enhance the diversity of data. We address the lack of diversity in data augmentation with image-to-image transformations parameterized by pre-trained text-to-image diffusion models. Our method edits images to change their semantics using an off-the-shelf diffusion model, and generalizes to novel visual concepts from a few labelled examples. We evaluate our approach on few-shot image classification tasks, and on a real-world weed recognition task, and observe an improvement in accuracy in tested domains.

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。

↑