3 papers
cs.LG2026
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,…
cs.LG2026
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…
cs.LG2025
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,…