Bayesian generative models can flag performance loss, bias, and out-of-distribution image content

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	López-Pérez, Miguel, Miani, Marco, Naranjo, Valery, Hauberg, Søren, Feragen, Aasa
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Are generative models fair? A study of racial bias in dermatological image generation
by: López-Pérez, Miguel, et al.
Published: (2025)

Laplacian Segmentation Networks Improve Epistemic Uncertainty Quantification
by: Zepf, Kilian, et al.
Published: (2023)

Fair Lung Disease Diagnosis from Chest CT via Gender-Adversarial Attention Multiple Instance Learning
by: Parikh, Aditya, et al.
Published: (2026)

Who Does Your Algorithm Fail? Investigating Age and Ethnic Bias in the MAMA-MIA Dataset
by: Parikh, Aditya, et al.
Published: (2025)

Navigating Uncertainty in Medical Image Segmentation
by: Zepf, Kilian, et al.
Published: (2024)

Patronus: Interpretable Diffusion Models with Prototypes
by: Weng, Nina, et al.
Published: (2025)

Investigating Label Bias and Representational Sources of Age-Related Disparities in Medical Segmentation
by: Parikh, Aditya, et al.
Published: (2025)

Towards Fairness under Label Bias in Image Segmentation: Impact, Measurement and Mitigation
by: Parikh, Aditya, et al.
Published: (2026)

Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation
by: Weng, Nina, et al.
Published: (2023)

Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis using Slice Discovery Methods
by: Olesen, Vincent, et al.
Published: (2024)

Explainable fetal ultrasound quality assessment with progressive concept bottleneck models
by: Lin, Manxi, et al.
Published: (2022)

Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections
by: Miani, Marco, et al.
Published: (2024)

Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information
by: Miani, Marco, et al.
Published: (2024)

Incorporating Clinical Guidelines through Adapting Multi-modal Large Language Model for Prostate Cancer PI-RADS Scoring
by: Zhang, Tiantian, et al.
Published: (2024)

Exploring bidirectional bounds for minimax-training of Energy-based models
by: Geng, Cong, et al.
Published: (2025)

Influence of Classification Task and Distribution Shift Type on OOD Detection in Fetal Ultrasound
by: Wong, Chun Kit, et al.
Published: (2025)

Initialization matters in few-shot adaptation of vision-language models for histopathological image classification
by: Meseguer, Pablo, et al.
Published: (2026)

Variational Autoencoding of Dental Point Clouds
by: Ye, Johan Ziruo, et al.
Published: (2023)

Tackling domain generalization for out-of-distribution endoscopic imaging
by: Teevno, Mansoor Ali, et al.
Published: (2024)

Zero-shot segmentation of skin tumors in whole-slide images with vision-language foundation models
by: Moreno, Santiago, et al.
Published: (2025)

SFLD: Reducing the content bias for AI-generated Image Detection
by: Gye, Seoyeon, et al.
Published: (2025)

Learning semantic image quality for fetal ultrasound from noisy ranking annotation
by: Lin, Manxi, et al.
Published: (2024)

MI-VisionShot: Few-shot adaptation of vision-language models for slide-level classification of histopathological images
by: Meseguer, Pablo, et al.
Published: (2024)

Are demographically invariant models and representations in medical imaging fair?
by: Petersen, Eike, et al.
Published: (2023)

A Framework for Exploring and Disentangling Intersectional Bias: A Case Study in Fetal Ultrasound
by: Elgebaly, Aya, et al.
Published: (2026)

Invertible generative models for inverse problems: mitigating representation error and dataset bias
by: Asim, Muhammad, et al.
Published: (2019)

Shortcut Learning in Medical Image Segmentation
by: Lin, Manxi, et al.
Published: (2024)

Weight Space Correlation Analysis: Quantifying Feature Utilization in Deep Learning Models
by: Wong, Chun Kit, et al.
Published: (2025)

How well are open sourced AI-generated image detection models out-of-the-box: A comprehensive benchmark study
by: Ren, Simiao, et al.
Published: (2026)

Using LLMs as prompt modifier to avoid biases in AI image generators
by: Peinl, René
Published: (2025)

Pinpoint Counterfactuals: Reducing social bias in foundation models via localized counterfactual generation
by: Sirotkin, Kirill, et al.
Published: (2024)

General Methods Make Great Domain-specific Foundation Models: A Case-study on Fetal Ultrasound
by: Ambsdorf, Jakob, et al.
Published: (2025)

Improving Adversarial Energy-Based Model via Diffusion Process
by: Geng, Cong, et al.
Published: (2024)

Dynamic watermarks in images generated by diffusion models
by: Chen, Yunzhuo, et al.
Published: (2025)

Mask-guided cross-image attention for zero-shot in-silico histopathologic image generation with a diffusion model
by: Winter, Dominik, et al.
Published: (2024)

Benchmarking histopathology foundation models in a multi-center dataset for skin cancer subtyping
by: Meseguer, Pablo, et al.
Published: (2025)

Less can be more: representational vs. stereotypical gender bias in facial expression recognition
by: Dominguez-Catena, Iris, et al.
Published: (2024)

Elucidating the design space of language models for image generation
by: Liu, Xuantong, et al.
Published: (2024)

Reparameterization invariance in approximate Bayesian inference
by: Roy, Hrittik, et al.
Published: (2024)

Category-aware EEG image generation based on wavelet transform and contrast semantic loss
by: Zhang, Enshang, et al.
Published: (2025)