Benchmarking Dependence Measures to Prevent Shortcut Learning in Medical Imaging
Medical imaging cohorts are often confounded by factors such as acquisition devices, hospital sites, patient backgrounds, and many more. As a result, deep learning models tend to learn spurious correlations instead of causally related features, limiting their generalizability to new and unseen data. This problem can be addressed by minimizing dependence measures between intermediate representations of task-related and non-task-related variables. These measures include mutual information, distance correlation, and the performance of adversarial classifiers. Here, we benchmark such dependence measures for the task of preventing shortcut learning. We study a simplified setting using Morpho-MNIST and a medical imaging task with CheXpert chest radiographs. Our results provide insights into how to mitigate confounding factors in medical imaging.
Code (1)
Tasks
BenchmarkingSimilar Papers 제목 키워드 기반
MedBench: A Comprehensive, Standardized, and Reliable Benchmarking System for Evaluating Chinese Medical Large Language Models
Ensuring the general efficacy and goodness for human beings from medical large language models (LLM) before real-world deployment is crucial. However, a widely accepted and accessible evaluation process for medical LLM, …
BenchmarkingDisrupting Model Training with Adversarial Shortcuts
When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventable with carefully designed dataset modifi…
BIG-bench Machine Learningimage-classificationImage ClassificationmodelNeurosymbolic Reasoning Shortcuts under the Independence Assumption
The ubiquitous independence assumption among symbolic concepts in neurosymbolic (NeSy) predictors is a convenient simplification: NeSy predictors use it to speed up probabilistic reasoning. Recent works like van Krieken …
Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study
Although deep learning models in medical imaging often achieve excellent classification performance, they can rely on shortcut learning, exploiting spurious correlations or confounding factors that are not causally relat…
Computational EfficiencyPreventing Shortcut Learning in Medical Image Analysis through Intermediate Layer Knowledge Distillation from Specialist Teachers
Deep learning models are prone to learning shortcut solutions to problems using spuriously correlated yet irrelevant features of their training data. In high-risk applications such as medical image analysis, this phenome…
Knowledge Distillation