Investigating and Improving Latent Density Segmentation Models for Aleatoric Uncertainty Quantification in Medical Imaging
cs.CV
Submitted: 2023-07-31
Updated: 2026-11-04
Terminology
Sources
- Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
- Auto-Encoding Variational Bayes
- A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities
- Effect of latent space distribution on the segmentation of images with multiple annotations
- Stochastic Segmentation with Conditional Categorical Diffusion Models
- Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
- Minimizing Trajectory Curvature of ODE-based Generative Models
- Denoising Diffusion Implicit Models
- InfoVAE: Information Maximizing Variational Autoencoders
- Variational Lossy Autoencoder
- Generating Sentences from a Continuous Space
- Layer Normalization
- Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
- Diagnosing and Enhancing VAE Models
- TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs