← Search

Martin Andreas Styner

2 accepted papers

2022

Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysis

NeurIPS 2022accept

Recent self-supervised advances in medical computer vision exploit the global and local anatomical self-similarity for pretraining prior to downstream tasks such as segmentation. However, current methods assume i.i.d. image acquisition, which is invalid in clinical study designs where follow-up long…

2021

Multiscale Score Matching for Out-of-Distribution Detection

ICLR 2021poster

We present a new methodology for detecting out-of-distribution (OOD) images by utilizing norms of the score estimates at multiple noise scales. A score is defined to be the gradient of the log density with respect to the input data. Our methodology is completely unsupervised and follows a straight f…