扩散模型通过反向去噪生成新数据,可用于改善不平衡数据分类性能。
Generative Modeling with Diffusion
- 先加噪声再反向去噪生成样本
- 可提升不平衡数据集上的分类准确率
- 适合对生成模型与数据增强感兴趣的读者
我们综述了扩散模型作为一种生成新样本的方法。生成模型近期被用于艺术生成(Stable Diffusion、Dall-E)和文本生成(ChatGPT)。扩散模型特别地通过向样本数据添加噪声,再逆转这一加噪过程来生成新样本。我们将正式定义加噪与去噪过程,并介绍训练与生成的算法。随后,探讨扩散模型在提升不平衡数据上分类性能方面的潜在应用。
原文摘要 · Abstract (English)
We provide an overview of the diffusion model as a method to generate new samples. Generative models have been recently adopted for tasks such as art generation (Stable Diffusion, Dall-E) and text generation (ChatGPT). Diffusion models in particular apply noise to sample data and then "reverse" this noising process to generate new samples. We will formally define these noising and denoising processes, then present algorithms to train and generate with a diffusion model. Afterward, we will explore a potential application of diffusion models in improving classifier performance on imbalanced data.
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。