Image de couverture de livre

How Diffusion Models Memorize

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kim, Juyeop, Kim, Songkuk, Lee, Jong-Seok
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion
par: Karnik, Sathwik, et autres
Publié: (2026)

Impact of Regularization on Calibration and Robustness: from the Representation Space Perspective
par: Park, Jonghyun, et autres
Publié: (2024)

DebFilter: Eradicating Biases Stashed in Value
par: Lee, Seung Hyuk, et autres
Publié: (2026)

Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detection
par: Oh, Ahyoung, et autres
Publié: (2026)

DESSERT: Diffusion-based Event-driven Single-frame Synthesis via Residual Training
par: Kong, Jiyun, et autres
Publié: (2025)

Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
par: Han, Hyeonggeun, et autres
Publié: (2025)

Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending
par: Ko, Junseok, et autres
Publié: (2026)

Progressive Learned Image Compression for Machine Perception
par: Kim, Jungwoo, et autres
Publié: (2025)

Coarse-to-Fine: Progressive Image Compression for Semantically Hierarchical Classification
par: Kim, Jungwoo, et autres
Publié: (2026)

Investigating Memorization in Video Diffusion Models
par: Chen, Chen, et autres
Publié: (2024)

Towards Memorization-Free Diffusion Models
par: Chen, Chen, et autres
Publié: (2024)

Low-Cost Self-Ensembles Based on Multi-Branch Transformation and Grouped Convolution
par: Lee, Hojung, et autres
Publié: (2024)

Memorization In Stable Diffusion Is Unexpectedly Driven by CLIP Embeddings
par: Kim, Bumjun, et autres
Publié: (2026)

Detecting, Explaining, and Mitigating Memorization in Diffusion Models
par: Wen, Yuxin, et autres
Publié: (2024)

SLIM: Semantic-based Low-bitrate Image compression for Machines by leveraging diffusion
par: Lee, Hyeonjin, et autres
Publié: (2025)

Diffusion Model for Dense Matching
par: Nam, Jisu, et autres
Publié: (2023)

Redistribute Ensemble Training for Mitigating Memorization in Diffusion Models
par: Guan, Xiaoliu, et autres
Publié: (2025)

Filtering Memorization from Parameter-Space in Diffusion Models
par: Zhe, Yu, et autres
Publié: (2026)

Key-point Guided Deformable Image Manipulation Using Diffusion Model
par: Oh, Seok-Hwan, et autres
Publié: (2024)

On Memorization in Diffusion Models
par: Gu, Xiangming, et autres
Publié: (2023)

Network Fission Ensembles for Low-Cost Self-Ensembles
par: Lee, Hojung, et autres
Publié: (2024)

Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerability
par: Hwang, Jaehui, et autres
Publié: (2023)

SC-Pro: Training-Free Framework for Defending Unsafe Image Synthesis Attack
par: Park, Junha, et autres
Publié: (2025)

When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class
par: Kim, Yujin, et autres
Publié: (2025)

Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models
par: Chen, Chen, et autres
Publié: (2025)

MemBench: Memorized Image Trigger Prompt Dataset for Diffusion Models
par: Hong, Chunsan, et autres
Publié: (2024)

Broken Memories: Detecting and Mitigating Memorization in Diffusion Models with Degraded Generations
par: Huang, Yuanmin, et autres
Publié: (2026)

Exploring Local Memorization in Diffusion Models via Bright Ending Attention
par: Chen, Chen, et autres
Publié: (2024)

Construction of Digital Terrain Maps from Multi-view Satellite Imagery using Neural Volume Rendering
par: Biberstein, Josef X., et autres
Publié: (2025)

Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation
par: Kim, Kihong, et autres
Publié: (2024)

Grid Diffusion Models for Text-to-Video Generation
par: Lee, Taegyeong, et autres
Publié: (2024)

Demystifying Foreground-Background Memorization in Diffusion Models
par: Di, Jimmy Z., et autres
Publié: (2025)

An Inversion-based Measure of Memorization for Diffusion Models
par: Ma, Zhe, et autres
Publié: (2024)

PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition
par: Lee, Sanghyeon, et autres
Publié: (2026)

How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects
par: Lee, Wonkwang, et autres
Publié: (2025)

Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness
par: Lee, Hangyeol, et autres
Publié: (2026)

RAD: Region-Aware Diffusion Models for Image Inpainting
par: Kim, Sora, et autres
Publié: (2024)

Modeling Visual Memorability Assessment with Autoencoders Reveals Characteristics of Memorable Images
par: Bagheri, Elham, et autres
Publié: (2024)

Adaptive Explicit Knowledge Transfer for Knowledge Distillation
par: Park, Hyungkeun, et autres
Publié: (2024)

Capacity Control is an Effective Memorization Mitigation Mechanism in Text-Conditional Diffusion Models
par: Dutt, Raman, et autres
Publié: (2024)