Institution profile

Aberystwyth University

Academic institutioneurope · gb
Official website
Research library7linked papers
Opportunities0open roles
Selected work

Representative Papers

Contrastive Mask Fidelity: Reference-Free Auditing of Ground-Truth Masks in Remote Sensing Semantic Segmentation

Aug 10, 2026

This study addresses the prevalent issues of coarse, misaligned, or incomplete manual annotations in remote sensing semantic segmentation, which often distort model evaluation. To tackle this, the authors propose a training-free, reference-free mask fidelity assessment method that constructs counterfactual image pairs—preserving and erasing the region within the mask—and leverages a frozen vision-language model to evaluate whether class-specific evidence is concentrated inside the mask and absent outside it. This approach enables, for the first time, reference-free auditing of annotation quality in remote sensing segmentation, revealing systematic labeling biases across categories and facilitating automatic refinement of supervision signals. The proposed Contrastive Mask Fidelity (CMF) metric achieves 81% agreement with expert judgments across ten remote sensing datasets, substantially outperforming existing methods, and CMF-guided supervision significantly enhances cross-domain transfer performance.

0 citationsRead paper

Understanding statistics for biomedical research through the lens of replication

Dec 15, 2025

This paper exposes a fundamental gap between statistical significance (e.g., one-sided *p* = 0.025) and actual replicability: under identical sample sizes, the probability of replicating an effect in the same direction is only ~0.975, while the probability of reproducing statistical significance is markedly lower (~0.283). Conventional power analysis overestimates replicability by ignoring sampling variance in the original effect estimate. To address this, we develop a replication probability model grounded in variance propagation—formally integrating the sampling variances of both original and replication effect estimates. Our framework unifies frequentist and Bayesian perspectives, discarding noninformative priors in favor of discretized probability mass analysis. The resulting theory yields novel, high-confidence replication sample-size criteria, providing both theoretical foundations and practical tools for robust biomedical validation studies.

0 citationsRead paper
Recent publications

Latest Papers

Contrastive Mask Fidelity: Reference-Free Auditing of Ground-Truth Masks in Remote Sensing Semantic Segmentation

Aug 10, 2026

This study addresses the prevalent issues of coarse, misaligned, or incomplete manual annotations in remote sensing semantic segmentation, which often distort model evaluation. To tackle this, the authors propose a training-free, reference-free mask fidelity assessment method that constructs counterfactual image pairs—preserving and erasing the region within the mask—and leverages a frozen vision-language model to evaluate whether class-specific evidence is concentrated inside the mask and absent outside it. This approach enables, for the first time, reference-free auditing of annotation quality in remote sensing segmentation, revealing systematic labeling biases across categories and facilitating automatic refinement of supervision signals. The proposed Contrastive Mask Fidelity (CMF) metric achieves 81% agreement with expert judgments across ten remote sensing datasets, substantially outperforming existing methods, and CMF-guided supervision significantly enhances cross-domain transfer performance.

0 citationsRead paper

Understanding statistics for biomedical research through the lens of replication

Dec 15, 2025

This paper exposes a fundamental gap between statistical significance (e.g., one-sided *p* = 0.025) and actual replicability: under identical sample sizes, the probability of replicating an effect in the same direction is only ~0.975, while the probability of reproducing statistical significance is markedly lower (~0.283). Conventional power analysis overestimates replicability by ignoring sampling variance in the original effect estimate. To address this, we develop a replication probability model grounded in variance propagation—formally integrating the sampling variances of both original and replication effect estimates. Our framework unifies frequentist and Bayesian perspectives, discarding noninformative priors in favor of discretized probability mass analysis. The resulting theory yields novel, high-confidence replication sample-size criteria, providing both theoretical foundations and practical tools for robust biomedical validation studies.

0 citationsRead paper