Image de couverture de livre

Unmasking Bias in Diffusion Model Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yu, Hu, Shen, Li, Huang, Jie, Li, Hongsheng, Zhao, Feng
Format:	Preprint
Publié:	2023
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

High-quality Image Dehazing with Diffusion Model
par: Yu, Hu, et autres
Publié: (2023)

FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment
par: Xu, Hang, et autres
Publié: (2025)

Deep Reward Supervisions for Tuning Text-to-Image Diffusion Models
par: Wu, Xiaoshi, et autres
Publié: (2024)

Implicit Bias Injection Attacks against Text-to-Image Diffusion Models
par: Huang, Huayang, et autres
Publié: (2025)

Uncovering the Text Embedding in Text-to-Image Diffusion Models
par: Yu, Hu, et autres
Publié: (2024)

DualFast: Dual-Speedup Framework for Fast Sampling of Diffusion Models
par: Yu, Hu, et autres
Publié: (2025)

Structure-Level Disentangled Diffusion for Few-Shot Chinese Font Generation
par: Li, Jie, et autres
Publié: (2026)

CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
par: Jiang, Dongzhi, et autres
Publié: (2024)

OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
par: Zhang, Guohui, et autres
Publié: (2026)

Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training
par: Niu, Ke, et autres
Publié: (2024)

BAMI: Training-Free Bias Mitigation in GUI Grounding
par: Zhang, Borui, et autres
Publié: (2026)

Highly Efficient Test-Time Scaling for T2I Diffusion Models with Text Embedding Perturbation
par: Xu, Hang, et autres
Publié: (2025)

Frequency Autoregressive Image Generation with Continuous Tokens
par: Yu, Hu, et autres
Publié: (2025)

Elucidating the Exposure Bias in Diffusion Models
par: Ning, Mang, et autres
Publié: (2023)

Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models
par: Li, Zejian, et autres
Publié: (2025)

Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement
par: Yang, Tao, et autres
Publié: (2024)

Seeing Right but Saying Wrong: Inter- and Intra-Layer Refinement in MLLMs without Training
par: Song, Shezheng, et autres
Publié: (2026)

Egocentric Bias in Vision-Language Models
par: Wang, Maijunxian, et autres
Publié: (2026)

Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models
par: Li, Wenhao, et autres
Publié: (2023)

MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture
par: Li, Hui, et autres
Publié: (2025)

Exposing the Copycat Problem of Imitation-based Planner: A Novel Closed-Loop Simulator, Causal Benchmark and Joint IL-RL Baseline
par: Zhou, Hui, et autres
Publié: (2025)

ADT: Tuning Diffusion Models with Adversarial Supervision
par: Shen, Dazhong, et autres
Publié: (2025)

Debiasing Classifiers by Amplifying Bias with Latent Diffusion and Large Language Models
par: Ko, Donggeun, et autres
Publié: (2024)

TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models
par: Shao, Wenqi, et autres
Publié: (2023)

Enhancing Vision-Language Model with Unmasked Token Alignment
par: Liu, Jihao, et autres
Publié: (2024)

Flexiffusion: Training-Free Segment-Wise Neural Architecture Search for Efficient Diffusion Models
par: Huang, Hongtao, et autres
Publié: (2025)

Dual-Channel Attention Guidance for Training-Free Image Editing Control in Diffusion Transformers
par: Li, Guandong
Publié: (2026)

Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data
par: Ma, Xudong
Publié: (2025)

From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information
par: Jiao, Qirui, et autres
Publié: (2024)

Latent-based Diffusion Model for Long-tailed Recognition
par: Han, Pengxiao, et autres
Publié: (2024)

Elucidating and Endowing the Diffusion Training Paradigm for General Image Restoration
par: Lu, Xin, et autres
Publié: (2025)

Multi-weather Cross-view Geo-localization Using Denoising Diffusion Models
par: Feng, Tongtong, et autres
Publié: (2024)

CoProSketch: Controllable and Progressive Sketch Generation with Diffusion Model
par: Zhan, Ruohao, et autres
Publié: (2025)

BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers
par: Seo, Jungwook, et autres
Publié: (2026)

Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question Answering
par: Shen, Zhixuan, et autres
Publié: (2024)

REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
par: Wang, Ziqiao, et autres
Publié: (2025)

SDiT: Spiking Diffusion Model with Transformer
par: Yang, Shu, et autres
Publié: (2024)

SKT: Integrating State-Aware Keypoint Trajectories with Vision-Language Models for Robotic Garment Manipulation
par: Li, Xin, et autres
Publié: (2024)

Casual Inference via Style Bias Deconfounding for Domain Generalization
par: Li, Jiaxi, et autres
Publié: (2025)

GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
par: Gao, Xin, et autres
Publié: (2025)