Scaling vision models by depth and parameter count does not consistently improve localisation-based explanation quality across architectures, datasets, and post-hoc methods; smaller models often perform comparably or better.
Machine Learning in Medicine
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
Introduces dashi, a Python library with unsupervised (information geometry-based) and supervised methods to quantify temporal and multi-source dataset shifts for trustworthy health AI.
Shapley regression replaces the linear predictor in logistic regression with a k-additive cooperative game to detect APDS and other rare diseases from symptom data while remaining transparent.
TBER describes representational emergence as a five-stage bootstrap process triggered by explanatory insufficiency in AI, biology, and science.
citing papers explorer
-
Scaling Vision Models Does Not Consistently Improve Localisation-Based Explanation Quality
Scaling vision models by depth and parameter count does not consistently improve localisation-based explanation quality across architectures, datasets, and post-hoc methods; smaller models often perform comparably or better.
-
dashi: A Python library for Dataset Shift Characterization to Support Trustworthy AI Development and Deployment
Introduces dashi, a Python library with unsupervised (information geometry-based) and supervised methods to quantify temporal and multi-source dataset shifts for trustworthy health AI.
-
Shapley Regression for Rare Disease Diagnosis Support: a case study on APDS
Shapley regression replaces the linear predictor in logistic regression with a k-additive cooperative game to detect APDS and other rare diseases from symptom data while remaining transparent.
-
Bootstrap Theory of Representational Emergence: Explanatory Insufficiency as a Driver of Representation Learning and World Models
TBER describes representational emergence as a five-stage bootstrap process triggered by explanatory insufficiency in AI, biology, and science.