paper-with-me

홈 › Papers

A Closer Look at Parameter-Efficient Tuning in Diffusion Models

2023-03-31 · Chendong Xiang, Fan Bao, Chongxuan Li, Hang Su, Jun Zhu

Large-scale diffusion models like Stable Diffusion are powerful and find various real-world applications while customizing such models by fine-tuning is both memory and time inefficient. Motivated by the recent progress in natural language processing, we investigate parameter-efficient tuning in large diffusion models by inserting small learnable modules (termed adapters). In particular, we decompose the design space of adapters into orthogonal factors -- the input position, the output position as well as the function form, and perform Analysis of Variance (ANOVA), a classical statistical approach for analyzing the correlation between discrete (design options) and continuous variables (evaluation metrics). Our analysis suggests that the input position of adapters is the critical factor influencing the performance of downstream tasks. Then, we carefully study the choice of the input position, and we find that putting the input position after the cross-attention block can lead to the best performance, validated by additional visualization analyses. Finally, we provide a recipe for parameter-efficient tuning in diffusion models, which is comparable if not superior to the fully fine-tuned baseline (e.g., DreamBooth) with only 0.75 \% extra parameters, across various customized tasks.

📄 PDF Abstract BibTeX arXiv:2303.18181

Code (1)

Xiang-cd/unet-finetune 공식 구현 pytorch

Tasks

Efficient Diffusion PersonalizationPosition

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

FreeFix: Boosting 3D Gaussian Splatting via Fine-Tuning-Free Diffusion Models

2026-01-28 · Hongyu Zhou, Zisen Shao, Sheng Miao, Pan Wang 외 arxiv

Neural Radiance Fields and 3D Gaussian Splatting have advanced novel view synthesis, yet still rely on dense inputs and often degrade at extrapolated views. Recent approaches leverage generative models, such as diffusion…

Novel View Synthesis

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

2024-05-27 · CVPR 2025 1 · Kai Wang, Mingjia Shi, Yukun Zhou, Zekai Li 외

Training diffusion models is always a computation-intensive task. In this paper, we introduce a novel speed-up method for diffusion model training, called, which is based on a closer look at time steps. Our key findings …

Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting

2024-06-02 · Jincheng Zhong, Xingzhuo Guo, Jiaxiang Dong, Mingsheng Long

Diffusion models have significantly advanced the field of generative modeling. However, training a diffusion model is computationally expensive, creating a pressing need to adapt off-the-shelf diffusion models for downst…

DenoisingTransfer Learning

SeeDiff: Off-the-Shelf Seeded Mask Generation from Diffusion Models

2025-07-26 · Joon Hyun Park, Kumju Jo, Sungyong Baik arxiv

Entrusted with the goal of pixel-level object classification, the semantic segmentation networks entail the laborious preparation of pixel-level annotation masks. To obtain pixel-level annotation masks for a given class …

Semantic SegmentationObject Localization

Don't Sweep your Learning Rate under the Rug: A Closer Look at Cross-modal Transfer of Pretrained Transformers

2021-07-26 · Danielle Rothermel, Margaret Li, Tim Rocktäschel, Jakob Foerster

Self-supervised pre-training of large-scale transformer models on text corpora followed by finetuning has achieved state-of-the-art on a number of natural language processing tasks. Recently, Lu et al. (2021, arXiv:2103.…