Imagen de Portada

Latent Diffusion U-Net Representations Contain Positional Embeddings and Anomalies

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Loos, Jonas, Linhardt, Lorenz
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Objective drives the consistency of representational similarity across datasets
por: Ciernik, Laure, et al.
Publicado: (2024)

Exploring Position Encoding in Diffusion U-Net for Training-free High-resolution Image Generation
por: Zhou, Feng, et al.
Publicado: (2025)

Human alignment of neural network representations
por: Muttenthaler, Lukas, et al.
Publicado: (2022)

FLIER: Few-shot Language Image Models Embedded with Latent Representations
por: Zhou, Zhinuo, et al.
Publicado: (2024)

Demystifying the Effect of Receptive Field Size in U-Net Models for Medical Image Segmentation
por: Loos, Vincent, et al.
Publicado: (2024)

U-REPA: Aligning Diffusion U-Nets to ViTs
por: Tian, Yuchuan, et al.
Publicado: (2025)

LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision
por: Li, Chunyu, et al.
Publicado: (2024)

Beyond the Noise: Aligning Prompts with Latent Representations in Diffusion Models
por: Ramos, Vasco, et al.
Publicado: (2025)

Boosting Latent Diffusion Models via Disentangled Representation Alignment
por: Page, John, et al.
Publicado: (2026)

SCAM: A Real-World Typographic Robustness Evaluation for Multimodal Foundation Models
por: Westerhoff, Justus, et al.
Publicado: (2025)

LDFaceNet: Latent Diffusion-based Network for High-Fidelity Deepfake Generation
por: Mehta, Dwij, et al.
Publicado: (2024)

CurvNet: Latent Contour Representation and Iterative Data Engine for Curvature Angle Estimation
por: Shao, Zhiwen, et al.
Publicado: (2024)

Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection
por: Cai, Zhaolin, et al.
Publicado: (2026)

AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error
por: Ricker, Jonas, et al.
Publicado: (2024)

Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding (D-RoPE)
por: Kung, Gustavo Chau Loo, et al.
Publicado: (2026)

Dynamic Importance in Diffusion U-Net for Enhanced Image Synthesis
por: Wang, Xi, et al.
Publicado: (2025)

Anatomical Positional Embeddings
por: Goncharov, Mikhail, et al.
Publicado: (2024)

U-Net with Hadamard Transform and DCT Latent Spaces for Next-day Wildfire Spread Prediction
por: Luo, Yingyi, et al.
Publicado: (2026)

Canonical Latent Representations in Conditional Diffusion Models
por: Xu, Yitao, et al.
Publicado: (2025)

AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model
por: Hu, Teng, et al.
Publicado: (2023)

HEART: Hyperspherical Embedding Alignment via Kent-Representation Traversal in Diffusion Models
por: Roy, Arani, et al.
Publicado: (2026)

Positional Embedding-Aware Activations
por: Shah, Kathan, et al.
Publicado: (2023)

Positive Semi-definite Latent Factor Grouping-Boosted Cluster-reasoning Instance Disentangled Learning for WSI Representation
por: Li, Chentao, et al.
Publicado: (2025)

AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion
por: Hu, Jie, et al.
Publicado: (2024)

RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection
por: Zhang, Ximiao, et al.
Publicado: (2024)

ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining
por: Yao, Xincheng, et al.
Publicado: (2025)

Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Framework
por: Jiang, Junkun, et al.
Publicado: (2024)

Continuous Memory Representation for Anomaly Detection
por: Lee, Joo Chan, et al.
Publicado: (2024)

One Attention, One Scale: Phase-Aligned Rotary Positional Embeddings for Mixed-Resolution Diffusion Transformer
por: Wu, Haoyu, et al.
Publicado: (2025)

Latent Uncertainty Representations for Video-based Driver Action and Intention Recognition
por: Vellenga, Koen, et al.
Publicado: (2025)

Automated Learning of Semantic Embedding Representations for Diffusion Models
por: Jiang, Limai, et al.
Publicado: (2025)

LatentCRF: Continuous CRF for Efficient Latent Diffusion
por: Ranasinghe, Kanchana, et al.
Publicado: (2024)

DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation Learning
por: Liu, Dongxu, et al.
Publicado: (2025)

Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
por: Hahm, Jaehoon, et al.
Publicado: (2024)

What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion
por: Yue, Zhengrong, et al.
Publicado: (2026)

CSE: Surface Anomaly Detection with Contrastively Selected Embedding
por: Thomine, Simon, et al.
Publicado: (2024)

ATAC-Net: Zoomed view works better for Anomaly Detection
por: Gupta, Shaurya, et al.
Publicado: (2024)

Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space
por: Zhou, Yifan, et al.
Publicado: (2025)

LLM-guided Instance-level Image Manipulation with Diffusion U-Net Cross-Attention Maps
por: Palaev, Andrey, et al.
Publicado: (2025)

Training-Free Style and Content Transfer by Leveraging U-Net Skip Connections in Stable Diffusion
por: Schaerf, Ludovica, et al.
Publicado: (2025)