activity
20182021
most citedUnderspecification Presents Challenges for Credibility in Modern Machine Learning

430 citations · 505 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CV202123 cited

Supervised Transfer Learning at Scale for Medical Imaging

Basil Mustafa, Aaron Loh, Jan Freyberg +12

Transfer learning is a standard technique to improve performance on tasks with limited data. However, for medical imaging, the value of transfer learning is less clear. This is lik…

eess.IV2021

Big Self-Supervised Models Advance Medical Image Classification

Shekoofeh Azizi, Basil Mustafa, Fiona Ryan +9

Self-supervised pretraining followed by supervised fine-tuning has seen success in image recognition, especially when labeled examples are scarce, but has received limited attentio…

cs.LG2020430 cited

Underspecification Presents Challenges for Credibility in Modern Machine Learning

Alexander D'Amour, Katherine Heller, Dan Moldovan +37

ML models often exhibit unexpectedly poor behavior when they are deployed in real-world domains. We identify underspecification as a key reason for these failures. An ML pipeline i…

cs.LG202052 cited

Contrastive Training for Improved Out-of-Distribution Detection

Jim Winkens, Rudy Bunel, Abhijit Guha Roy +10

Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems. This paper proposes and investiga…

cs.CV2018

Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy

Stanislav Nikolov, Sam Blackwell, Alexei Zverovitch +26

Over half a million individuals are diagnosed with head and neck cancer each year worldwide. Radiotherapy is an important curative treatment for this disease, but it requires manua…