Introduces architecture distributions for stochastic segmentation by sampling discrete architectures from a learned distribution, trained via set-level IoU-based supervision and evolutionary candidate bank construction, claiming SOTA on LIDC-IDRI.
A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Medical imaging only indirectly measures the molecular identity of the tissue within each voxel, which often produces only ambiguous image evidence for target measures of interest, like semantic segmentation. This diversity and the variations of plausible interpretations are often specific to given image regions and may thus manifest on various scales, spanning all the way from the pixel to the image level. In order to learn a flexible distribution that can account for multiple scales of variations, we propose the Hierarchical Probabilistic U-Net, a segmentation network with a conditional variational auto-encoder (cVAE) that uses a hierarchical latent space decomposition. We show that this model formulation enables sampling and reconstruction of segmenations with high fidelity, i.e. with finely resolved detail, while providing the flexibility to learn complex structured distributions across scales. We demonstrate these abilities on the task of segmenting ambiguous medical scans as well as on instance segmentation of neurobiological and natural images. Our model automatically separates independent factors across scales, an inductive bias that we deem beneficial in structured output prediction tasks beyond segmentation.
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
A harmonized probabilistic model with adaptive feature conditioning and high-frequency prompt modules disentangles acquisition artifacts from rater variability to produce personalized yet consistent multi-rater segmentations, showing SOTA results on LIDC-IDRI and NPC-170.
A logit-space SVGP framework explicitly models annotator bias and variance to improve uncertainty calibration in multi-rater probabilistic segmentation while keeping accuracy comparable to prior methods.
VarDeepPCA is a sampling-free variational DNN plugin that learns anatomical geometry distributions from tiny ID training sets to refine OOD segmentations and estimate uncertainty.
An information-theoretic optimization framework for task-adapted CS-MRI enables adaptive sampling at arbitrary ratios and probabilistic inference for uncertainty while supporting joint reconstruction-task or privacy-focused scenarios.
Conditional flow matching produces segmentation samples whose pixel-wise variance quantifies aleatoric uncertainty in medical images by learning an exact density rather than relying on stochastic diffusion sampling.
citing papers explorer
-
Neural Architecture Distributions: A New Paradigm for Stochastic Segmentation
Introduces architecture distributions for stochastic segmentation by sampling discrete architectures from a learned distribution, trained via set-level IoU-based supervision and evolutionary candidate bank construction, claiming SOTA on LIDC-IDRI.
-
Harmonized Feature Conditioning and Frequency-Prompt Personalization for Multi-Rater Medical Segmentation
A harmonized probabilistic model with adaptive feature conditioning and high-frequency prompt modules disentangles acquisition artifacts from rater variability to produce personalized yet consistent multi-rater segmentations, showing SOTA results on LIDC-IDRI and NPC-170.
-
Interpretable Probabilistic Medical Image Segmentation via Gaussian Process with Explicit Modelling of Annotation Bias and Variability
A logit-space SVGP framework explicitly models annotator bias and variance to improve uncertainty calibration in multi-rater probabilistic segmentation while keeping accuracy comparable to prior methods.
-
Learning a Sampling-Free Variational DNN Plugin from Tiny Training Sets to Refine OOD Segmentation With Uncertainty Estimation
VarDeepPCA is a sampling-free variational DNN plugin that learns anatomical geometry distributions from tiny ID training sets to refine OOD segmentations and estimate uncertainty.
-
Information-Theoretic Optimization for Task-Adapted Compressed Sensing Magnetic Resonance Imaging
An information-theoretic optimization framework for task-adapted CS-MRI enables adaptive sampling at arbitrary ratios and probabilistic inference for uncertainty while supporting joint reconstruction-task or privacy-focused scenarios.
-
Aleatoric Uncertainty Medical Image Segmentation Estimation via Flow Matching
Conditional flow matching produces segmentation samples whose pixel-wise variance quantifies aleatoric uncertainty in medical images by learning an exact density rather than relying on stochastic diffusion sampling.