arXiv Computer Vision

Uncertainty Estimation in Pathology Foundation Models via Deep Mutual Learning

The paper introduces DICE, a plug‑and‑play framework that ensembles multiple frozen pathology foundation models (PFMs) and estimates uncertainty from their consensus. By aligning ensemble members through deep mutual learning, DICE theoretically bounds epistemic uncertainty and localizes abnormalities at the patch level without explicit supervision. Experiments on three whole‑slide image benchmarks show that DICE provides reliable uncertainty estimates, accurately flags failure‑prone cases in both in‑ and out‑of‑distribution settings, and matches or surpasses state‑of‑the‑art baselines in classification, calibration, and localization.

arXiv AI

Sep 24

Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification

The study investigates whether pathology foundation models (PFMs) carry center-related biases into whole-slide image (WSI) classification. By training models with increasing class-center correlations and evaluating six PFMs across four datasets and two MIL aggregators, the authors introduce the Area Under the Cramér's V Curve (AUCC) to measure both accuracy and degradation due to spurious correlations. Results reveal that center information propagates to WSI predictions, with robustness varying by PFM and MIL strategy, and that ComBat harmonization does not consistently improve robustness.

By Il\'an Carretero, Pablo Meseguer, Roc\'io del Amor, Valery Naranjo

computer-vision benchmarks

Hugging Face Trending Papers

Aug 11

Uncertainty-Aware and Explainable Ensemble Deep Learning Framework for Multi-Class Skin Lesion Classification

Skin cancer diagnosis from dermoscopic images remains challenging due to high intra-class variability, inter-class similarity, class imbalance, and the limited interpretability of deep learning models. This paper proposes an uncertainty-aware and explainable deep learning framework for multi-class skin lesion classification.

llms computer-vision safety

arXiv Machine Learning

Jun 18

Quantification of Uncertainty with Adversarial Models in Medical Image Segmentation

arXiv:2606. 18860v1 Announce Type: cross Abstract: Reliable pixel-level uncertainty quantification holds the potential to transform clinical workflows by enabling high-fidelity longitudinal monitoring and distinguishing true pathological changes from artifacts.

By Hana Jebril, Thomas Pinetz, G\"unter Klambauer, Hrvoje Bogunovi\'c

computer-vision safety

arXiv Machine Learning

Jun 2

DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Prediction

arXiv:2510. 00053v2 Announce Type: replace-cross Abstract: Pathology whole-slide images (WSIs) are widely used for cancer survival analysis because of their comprehensive histopathological information at both cellular and tissue levels, enabling quantitative, large-scale, and prognostically rich tumor feature analysis.

By Yucheng Xing, Ling Huang, Jingying Ma, Ruping Hong, Jiangdong Qiu, Pei Liu, Kai He, Huazhu Fu, Mengling Feng

safety

arXiv AI

Aug 13

Uncertainty-Aware and Explainable Ensemble Deep Learning Framework for Multi-Class Skin Lesion Classification

arXiv:2608. 11280v1 Announce Type: cross Abstract: Skin cancer diagnosis from dermoscopic images remains challenging due to high intra-class variability, inter-class similarity, class imbalance, and the limited interpretability of deep learning models.

By Rofiqul Islam, Lilatul Ferdouse

llms computer-vision safety

arXiv AI

Oct 1

Towards Trustworthy AI for Glioma Diagnosis: A Task-Aware Evaluation of Uncertainty Quantification

arXiv:2609.39429v1 Announce Type: cross Abstract: Uncertainty Quantification (UQ) is a key requirement for trustworthy AI in high-stakes medical image analysis. In this work, we evaluate UQ in a mult...

By Gonzalo Esteban Mosquera Rojas, Sebastian R. van der Voort, Carolin M. Pirkl, Sandeep Kaushik, Marion Smits, Stefan Klein

computer-vision safety

arXiv Machine Learning

Jun 17

Learning Credal Ensembles via Distributionally Robust Optimization

arXiv:2602. 08470v3 Announce Type: replace Abstract: Credal predictors are models that are aware of epistemic uncertainty and produce a convex set of probabilistic predictions.

By Kaizheng Wang, Ghifari Adam Faza, Fabio Cuzzolin, Siu Lun Chau, David Moens, Hans Hallez

benchmarks

Hugging Face Trending Papers

3d ago

Estimating Performance for Safe Deployment of Machine Learning Models

The main challenge in applying deep neural networks to real-world scenarios lies in distributional discrepancies between training and test datasets, often caused by variations in data acquisition cond...

computer-vision benchmarks safety

arXiv Machine Learning

2d ago

Estimating Performance for Safe Deployment of Machine Learning Models

The paper introduces MOVAL, a model evaluation tool that estimates performance of deep neural networks on unlabeled test data by calibrating class-wise confidence scores. MOVAL mitigates issues from distributional shifts and class imbalance, enabling estimation of metrics beyond accuracy such as F1-Score and AUC. Experiments on natural and medical image datasets demonstrate state‑of‑the‑art results across classification and segmentation tasks, providing accurate class, instance, and pixel‑level performance estimates for safe deployment.

By Zeju Li, Konstantinos Kamnitsas, Mobarakol Islam, Melanie Roschewitz, Cheng Ouyang, Chen Chen, Ben Glocker

computer-vision benchmarks safety

arXiv Machine Learning

Aug 3

MoPET: Parameter-Efficient Mixture-of-Experts for Unified Medical Image Classification

arXiv:2607. 29462v1 Announce Type: cross Abstract: Adapting deep learning models to profound clinical heterogeneity typically relies on parameter-efficient fine-tuning (PEFT) to avoid the severe overfitting associated with full end-to-end network updates.

By Sebastian Doerrich, Daniel W\"urtinger, Francesco Di Salvo, Shyam Nandan Rai, Christian Ledig

computer-vision fine-tuning benchmarks

arXiv Computer Vision

Oct 1

Rethinking Uncertainty Quantification and Entanglement in Image Segmentation

arXiv:2603.18792v3 Announce Type: replace Abstract: Uncertainty quantification (UQ) is crucial in safety-critical applications such as medical image segmentation. Total uncertainty is typically decom...

By Jakob L{\o}nborg Christensen, Vedrana Andersen Dahl, Morten Rieger Hannemose, Anders Bjorholm Dahl, Christian F. Baumgartner

diffusion computer-vision safety

arXiv Machine Learning

Aug 18

Beyond Boundary Noise: Aggregated Aleatoric Uncertainty Fails to Capture Presence Ambiguity in 3D Lung Nodule Segmentation

arXiv:2608. 14766v1 Announce Type: cross Abstract: Uncertainty estimation is critical for the safe clinical deployment of deep learning in medical image segmentation, with aleatoric uncertainty theoretically designed to capture irreducible data ambiguity.

By Simon Baur, Arne Schernich, Ekin B\"oke, Wojciech Samek, Jackie Ma

computer-vision safety

Related stories