Imagen de Portada

Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Ma, Xudong
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data
por: Aali, Asad, et al.
Publicado: (2024)

Leveraging Model Guidance to Extract Training Data from Personalized Diffusion Models
por: Wu, Xiaoyu, et al.
Publicado: (2024)

Slight Corruption in Pre-training Data Makes Better Diffusion Models
por: Chen, Hao, et al.
Publicado: (2024)

DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization
por: Hosseintabar, Danial, et al.
Publicado: (2025)

StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Data
por: Mu, Yuxuan, et al.
Publicado: (2025)

Unmasking Bias in Diffusion Model Training
por: Yu, Hu, et al.
Publicado: (2023)

Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training
por: Niu, Ke, et al.
Publicado: (2024)

Training-Free Representation Guidance for Diffusion Models with a Representation Alignment Projector
por: Zu, Wenqiang, et al.
Publicado: (2026)

StereoDiffusion: Training-Free Stereo Image Generation Using Latent Diffusion Models
por: Wang, Lezhong, et al.
Publicado: (2024)

FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding
por: Yang, Jinghan, et al.
Publicado: (2026)

Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data
por: Daras, Giannis, et al.
Publicado: (2024)

BootPIG: Bootstrapping Zero-shot Personalized Image Generation Capabilities in Pretrained Diffusion Models
por: Purushwalkam, Senthil, et al.
Publicado: (2024)

Autoguided Online Data Curation for Diffusion Model Training
por: Pais, Valeria, et al.
Publicado: (2025)

Effective Data Augmentation With Diffusion Models
por: Trabucco, Brandon, et al.
Publicado: (2023)

Diffusion Models as Data Mining Tools
por: Siglidis, Ioannis, et al.
Publicado: (2024)

IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis
por: Shao, Shitong, et al.
Publicado: (2024)

Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data
por: Sun, Zeyi, et al.
Publicado: (2024)

Leveraging Diffusion Perturbations for Measuring Fairness in Computer Vision
por: Lui, Nicholas, et al.
Publicado: (2023)

X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations
por: Pace, Maximus A., et al.
Publicado: (2025)

Leveraging Vision-Language Models to Select Trustworthy Super-Resolution Samples Generated by Diffusion Models
por: Korkmaz, Cansu, et al.
Publicado: (2025)

Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models
por: Li, Zejian, et al.
Publicado: (2025)

Upsample Guidance: Scale Up Diffusion Models without Training
por: Hwang, Juno, et al.
Publicado: (2024)

Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training
por: Gao, Jiaxuan, et al.
Publicado: (2026)

DMin: Scalable Training Data Influence Estimation for Diffusion Models
por: Lin, Huawei, et al.
Publicado: (2024)

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
por: Chen, Lei, et al.
Publicado: (2024)

Improved Noise Schedule for Diffusion Training
por: Hang, Tiankai, et al.
Publicado: (2024)

Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness
por: Wu, Boqian, et al.
Publicado: (2024)

Yuan-TecSwin: A text conditioned Diffusion model with Swin-transformer blocks
por: Wu, Shaohua, et al.
Publicado: (2025)

PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptions
por: Ma, Sihan, et al.
Publicado: (2024)

TAIGen: Training-Free Adversarial Image Generation via Diffusion Models
por: Roy, Susim, et al.
Publicado: (2025)

Detail++: Training-Free Detail Enhancer for Text-to-Image Diffusion Models
por: Chen, Lifeng, et al.
Publicado: (2025)

On Equivariance and Fast Sampling in Video Diffusion Models Trained with Warped Noise
por: Liu, Chao, et al.
Publicado: (2025)

FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models
por: So, Junhyuk, et al.
Publicado: (2023)

FashionFlow: Leveraging Diffusion Models for Dynamic Fashion Video Synthesis from Static Imagery
por: Islam, Tasin, et al.
Publicado: (2023)

Accelerating Diffusion Models with One-to-Many Knowledge Distillation
por: Zhang, Linfeng, et al.
Publicado: (2024)

SDiT: Spiking Diffusion Model with Transformer
por: Yang, Shu, et al.
Publicado: (2024)

Exploring Diffusion Models' Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks
por: Wu, Xiaoyu, et al.
Publicado: (2024)

DiffVAS: Diffusion-Guided Visual Active Search in Partially Observable Environments
por: Sarkar, Anindya, et al.
Publicado: (2026)

StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model
por: Zhou, Ziyin, et al.
Publicado: (2024)

FAIRT2V: Training-Free Debiasing for Text-to-Video Diffusion Models
por: Zhong, Haonan, et al.
Publicado: (2026)