paper-with-me

홈 › Papers

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 downstream generation tasks. Current fine-tuning methods focus on parameter-efficient transfer learning but overlook the fundamental transfer characteristics of diffusion models. In this paper, we investigate the transferability of diffusion models and observe a monotonous chain of forgetting trend of transferability along the reverse process. Based on this observation and novel theoretical insights, we present Diff-Tuning, a frustratingly simple transfer approach that leverages the chain of forgetting tendency. Diff-Tuning encourages the fine-tuned model to retain the pre-trained knowledge at the end of the denoising chain close to the generated data while discarding the other noise side. We conduct comprehensive experiments to evaluate Diff-Tuning, including the transfer of pre-trained Diffusion Transformer models to eight downstream generations and the adaptation of Stable Diffusion to five control conditions with ControlNet. Diff-Tuning achieves a 26% improvement over standard fine-tuning and enhances the convergence speed of ControlNet by 24%. Notably, parameter-efficient transfer learning techniques for diffusion models can also benefit from Diff-Tuning.

📄 PDF Abstract BibTeX arXiv:2406.00773

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingTransfer Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Focus 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning

2025-10-20 · Jinseong Park, Mijung Park arxiv

Data unlearning aims to remove the influence of specific training samples from a trained model. In fine-tuning methods, data unlearning relies primarily on loss maximization over forget samples, which often leads to qual…

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment

2025-01-01 · CVPR 2025 1 · Johannes Schusterbauer, Ming Gui, Frank Fundel, Björn Ommer

Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computati…

ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning

2025-07-30 · Xiefan Guo, Miaomiao Cui, Liefeng Bo, Di Huang arxiv

Backpropagation-based approaches aim to align diffusion models with reward functions through end-to-end backpropagation of the reward gradient within the denoising chain, offering a promising perspective. However, due to…

Low-Rank Continual Personalization of Diffusion Models

2024-10-07 · Łukasz Staniszewski, Katarzyna Zaleska, Kamil Deja

Recent personalization methods for diffusion models, such as Dreambooth, allow fine-tuning pre-trained models to generate new concepts. However, applying these techniques across multiple tasks in order to include, e.g., …

Continual Learning

Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models

2026-05-27 · Ken Takeda, Masafumi Oizumi, Ryo Karakida arxiv

Generative models, including diffusion models, are increasingly used as foundation models and adapted through sequential fine-tuning, making continual learning an essential problem setting. However, continual learning in…

Continual Learning