6 papers
Normal Guidance is what Attention Needs
Ethan Harvey, Dennis Johan Loevlie, Michael C. Hughes
We consider training classifiers for 3D medical images using only one binary label for the entire volume rather than a label for each 2D slice. In such weakly supervised settings,…
A Multi-Dataset Benchmark of Multiple Instance Learning for 3D Neuroimage Classification
Ethan Harvey, Dennis Johan Loevlie, Amir Ali Satani +3
Despite being resource-intensive to train, 3D convolutional neural networks (CNNs) have been the standard approach to classify CT and MRI scans. Recent work suggests that deep mult…
Occam's Razor is Only as Sharp as Your ELBO
Ethan Harvey, Michael C. Hughes
The marginal likelihood, also known as the evidence, is regarded as a mathematical embodiment of Occam's razor, enabling model selection that avoids overfitting. The evidence lower…
Learning Hyperparameters via a Data-Emphasized Variational Objective
Ethan Harvey, Mikhail Petrov, Michael C. Hughes
When training large models on limited data, avoiding overfitting is paramount. Common grid search or smarter search methods rely on expensive separate runs for each candidate hyper…
Synthetic Data Reveals Generalization Gaps in Correlated Multiple Instance Learning
Ethan Harvey, Dennis Johan Loevlie, Michael C. Hughes
Multiple instance learning (MIL) is often used in medical imaging to classify high-resolution 2D images by processing patches or classify 3D volumes by processing slices. However,…
Learning the Regularization Strength for Deep Fine-Tuning via a Data-Emphasized Variational Objective
Ethan Harvey, Mikhail Petrov, Michael C. Hughes
A number of popular transfer learning methods rely on grid search to select regularization hyperparameters that control over-fitting. This grid search requirement has several key d…