Training Diffusion-based Generative Models with Limited Data
Zhaoyu Zhang, Yang Hua, Guanxiong Sun, Hui Wang, Seán F. McLoone
Abstract
Diffusion-based generative models (diffusion models) often require a large amount of data to train a score-based model that learns the score function of the data distribution through denoising score matching. However, collecting and cleaning such data can be expensive, time-consuming, and even infeasible. In this paper, we present a novel theoretical insight for diffusion models that two factors, i.e., the denoiser function hypothesis space and the number of training samples, can affect the denoising score matching error of all training samples. Based on this theoretical insight, it is evident that minimizing the total denoising score matching error is challenging within the denoiser function hypothesis space in existing methods, when training diffusion models with limited data. To address this, we propose a new diffusion model called Limited Data Diffusion (LD-Diffusion), which consists of two main components: a compressing model and a novel mixed augmentation with fixed probability (MAFP) strategy. Specifically, the compressing model can constrain the complexity of the denoiser function hypothesis space and MAFP can effectively increase the training samples by providing more informative guidance than existing data augmentation methods in the compressed hypothesis space. Extensive experiments on several datasets demonstrate that LD-Diffusion can achieve better performance compared to other diffusion models. Codes are available at https://github. com/zzhang05/LD-Diffusion. Training Diffusion-based Generative Models with Limited Data FFHQ-100 FID 50.73 FFHQ-100 FID 28.51 (-22.22) LD-Diffusion FFHQ-1K FID 17.76 (-12.99) FFHQ-2K FID 27.17 FFHQ-2K FID 14.36 (-12.81
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- High-Resolution Image Synthesis with Latent Diffusion Models cites Diffusion Models Beat GANs on Image Synthesis
- High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
- A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors cites High-Resolution Image Synthesis with Latent Diffusion Models
- A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors cites Denoising Diffusion Probabilistic Models
- Diffusion Models Beat GANs on Image Synthesis cites Denoising Diffusion Probabilistic Models
- WILD-Diffusion: A WDRO Inspired Training Method for Diffusion Models under Limited Data cites High-Resolution Image Synthesis with Latent Diffusion Models
- WILD-Diffusion: A WDRO Inspired Training Method for Diffusion Models under Limited Data cites Diffusion Models Beat GANs on Image Synthesis
- WILD-Diffusion: A WDRO Inspired Training Method for Diffusion Models under Limited Data cites Denoising Diffusion Probabilistic Models
- Directly Denoising Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
- Directly Denoising Diffusion Models cites Diffusion Models Beat GANs on Image Synthesis
- Directly Denoising Diffusion Models cites Denoising Diffusion Probabilistic Models
- Directly Denoising Diffusion Models cites Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites High-Resolution Image Synthesis with Latent Diffusion Models
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Diffusion Models Beat GANs on Image Synthesis
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Denoising Diffusion Probabilistic Models
Cited by top-tier papers2
Builds on39
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 13,211 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 11,724 citations
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
Related papers
- Accelerating Diffusion Model Training under Minimal Budgets: A Condensation-Based PerspectiveRui Huang, Shitong Shao, Zikai Zhou, Pukun Zhao et al.CVPR 2026 · 7 citations
- Towards Effective Data-Free Knowledge Distillation via Diverse Diffusion AugmentationMuquan Li, Dongyang Zhang, Tao He, Xiurui Xie et al.ACM MM 2024 · 5 citations
- How Much is a Noisy Image Worth? Data Scaling Laws for Ambient DiffusionGiannis Daras, Yeshwanth Cherapanamjeri, Constantinos DaskalakisICLR 2025
- Maximum Likelihood Training of Score-Based Diffusion ModelsYang Song, Conor Durkan, Iain Murray, Stefano ErmonNeurIPS 2021 · 958 citations
- UDPM: Upsampling Diffusion Probabilistic ModelsShady Abu-Hussein, Raja GiryesNeurIPS 2024 · 10 citations
