提出一种无需额外数据的图像生成正则化方法，提升扩散模型性能。
Diffuse and Disperse: Image Generation with Representation Regularization
- 设计分散损失函数，让隐空间表示更分散，增强特征表达。
- 在ImageNet上多个模型测试中均超越主流基线，效果稳定提升。
- 无需预训练、无额外参数，可直接插入现有扩散模型使用。
过去十年间，基于扩散的生成模型的发展与表征学习进展基本脱节。这些模型通常依赖回归目标，缺乏显式正则化。本文提出一种名为「Dispersive Loss」的简单即插即用正则化器，有效提升扩散生成模型性能。该损失函数促使内部表征在隐空间中分散，类似于对比自监督学习，但无需正样本对，因此不干扰回归采样过程。相比近期的表征对齐（REPA）方法，本方案自包含且极简，无需预训练、无额外参数、不需外部数据。我们在ImageNet数据集上对多种模型进行评估，结果表明其在广泛使用的强基线上均有持续改进。期望本工作能弥合生成建模与表征学习之间的鸿沟。
原文摘要 · Abstract (English)
The development of diffusion-based generative models over the past decade has largely proceeded independently of progress in representation learning. These diffusion models typically rely on regression-based objectives and generally lack explicit regularization. In this work, we propose \textit{Dispersive Loss}, a simple plug-and-play regularizer that effectively improves diffusion-based generative models. Our loss function encourages internal representations to disperse in the hidden space, analogous to contrastive self-supervised learning, with the key distinction that it requires no positive sample pairs and therefore does not interfere with the sampling process used for regression. Compared to the recent method of representation alignment (REPA), our approach is self-contained and minimalist, requiring no pre-training, no additional parameters, and no external data. We evaluate Dispersive Loss on the ImageNet dataset across a range of models and report consistent improvements over widely used and strong baselines. We hope our work will help bridge the gap between generative modeling and representation learning.
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。