Web: http://arxiv.org/abs/2206.07155

June 16, 2022, 1:10 a.m. | Anil Palepu, Andrew L Beam

cs.LG updates on arXiv.org arxiv.org

Deep learning models trained in a fully supervised manner have been shown to
rely on so-called "shortcut" features. Shortcut features are inputs that are
associated with the outcome of interest in the training data, but are either no
longer associated or not present in testing or deployment settings. Here we
provide experiments that show recent self-supervised models trained on images
and text provide more robust image representations and reduce the model's
reliance on visual shortcut features on a realistic medical …

arxiv features images lg on text

More from arxiv.org / cs.LG updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY