paper-with-me

홈 › Papers

Towards Memorization-Free Diffusion Models

2024-04-01 · CVPR 2024 1 · Chen Chen, Daochang Liu, Chang Xu

Pretrained diffusion models and their outputs are widely accessible due to their exceptional capacity for synthesizing high-quality images and their open-source nature. The users, however, may face litigation risks owing to the models' tendency to memorize and regurgitate training data during inference. To address this, we introduce Anti-Memorization Guidance (AMG), a novel framework employing three targeted guidance strategies for the main causes of memorization: image and caption duplication, and highly specific user prompts. Consequently, AMG ensures memorization-free outputs while maintaining high image quality and text alignment, leveraging the synergy of its guidance methods, each indispensable in its own right. AMG also features an innovative automatic detection system for potential memorization during each step of inference process, allows selective application of guidance strategies, minimally interfering with the original sampling process to preserve output utility. We applied AMG to pretrained Denoising Diffusion Probabilistic Models (DDPM) and Stable Diffusion across various generation tasks. The results demonstrate that AMG is the first approach to successfully eradicates all instances of memorization with no or marginal impacts on image quality and text-alignment, as evidenced by FID and CLIP scores.

📄 PDF Abstract BibTeX arXiv:2404.00922

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingMemorization

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…
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Classifier-Free Guidance inside the Attraction Basin May Cause Memorization

2024-11-23 · CVPR 2025 1 · Anubhav Jain, Yuya Kobayashi, Takashi Shibuya, Yuhta Takida 외

Diffusion models are prone to exactly reproduce images from the training data. This exact reproduction of the training data is concerning as it can lead to copyright infringement and/or leakage of privacy-sensitive infor…

DenoisingMemorization

How Diffusion Models Memorize

2025-09-30 · Juyeop Kim, Songkuk Kim, Jong-Seok Lee arxiv

Despite their success in image generation, diffusion models can memorize training data, raising serious privacy and copyright concerns. Although prior work has sought to characterize, detect, and mitigate memorization, t…

Image Generation

Filtering Memorization from Parameter-Space in Diffusion Models

2026-05-11 · Yu Zhe, Yang Jiayan, Wei Junhao, Yu-Lin Tsai 외 arxiv

Low-Rank Adaptation (LoRA) has become a widely used mechanism for customizing diffusion models, enabling users to inject new visual concepts or styles through lightweight parameter updates. However, LoRAs can memorize tr…

CAPTAIN: Semantic Feature Injection for Memorization Mitigation in Text-to-Image Diffusion Models

2025-12-11 · Tong Zhang, Carlos Hinojosa, Bernard Ghanem arxiv

Diffusion models can unintentionally reproduce training examples, raising privacy and copyright concerns as these systems are increasingly deployed at scale. Existing inference-time mitigation methods typically manipulat…

Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability

2026-01-28 · Rohan Asthana, Vasileios Belagiannis arxiv

Diffusion-based image generative models produce high-fidelity images through iterative denoising but remain vulnerable to memorization, where they unintentionally reproduce exact copies or parts of training images. Recen…