This paper presents our method for the generative track of The First Dataset Distillation Challenge at ECCV 2024. Since the diffusion model has become the mainstay of generative models because of its high-quality generative effects, we focus on distillation methods based on the diffusion model. Considering that the track can only generate a fixed number of images in 10 minutes using a generative model for CIFAR-100 and Tiny-ImageNet datasets, we need to use a generative model that can generate images at high speed. In this study, we proposed a novel generative dataset distillation method based on Stable Diffusion. Specifically, we use the SDXL-Turbo model which can generate images at high speed and quality. Compared to other diffusion models that can only generate images per class (IPC) = 1, our method can achieve an IPC = 10 for Tiny-ImageNet and an IPC = 20 for CIFAR-100, respectively. Additionally, to generate high-quality distilled datasets for CIFAR-100 and Tiny-ImageNet, we use the class information as text prompts and post data augmentation for the SDXL-Turbo model. Experimental results show the effectiveness of the proposed method, and we achieved third place in the generative track of the ECCV 2024 DD Challenge. Codes are available at https://github.com/Guang000/BANKO.

翻译：本文介绍了我们在ECCV 2024首届数据集蒸馏挑战赛生成式赛道中所采用的方法。鉴于扩散模型因其高质量的生成效果已成为生成模型的主流，我们专注于基于扩散模型的蒸馏方法。考虑到该赛道要求使用生成模型在10分钟内为CIFAR-100和Tiny-ImageNet数据集生成固定数量的图像，我们需要采用能够高速生成图像的生成模型。在本研究中，我们提出了一种基于Stable Diffusion的新型生成式数据集蒸馏方法。具体而言，我们采用了能够高速且高质量生成图像的SDXL-Turbo模型。相较于其他仅能实现每类图像数（IPC）=1的扩散模型，我们的方法在Tiny-ImageNet上可实现IPC=10，在CIFAR-100上可实现IPC=20。此外，为了为CIFAR-100和Tiny-ImageNet生成高质量的蒸馏数据集，我们使用类别信息作为文本提示，并对SDXL-Turbo模型进行后置数据增强。实验结果表明了所提方法的有效性，我们在ECCV 2024数据集蒸馏挑战赛的生成式赛道中获得了第三名。代码可在https://github.com/Guang000/BANKO获取。