hendrycksetal
How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios
Mantas Mazeika, Eric Tang, Andy Zou, Steven Basart, Jun Shern Chan, Dawn Song, David Forsyth, Jacob Steinhardt, Dan Hendrycks
Videos are a rich source of data that depict vast quantities of information about humans and the world. As deep learning has progressed, models havebegun to reliably exhibit various aspects of video understanding, including action recognition (Kay etal.,2017a),object
Technology:
RegMixup: MixupasaRegularizerCanSurprisingly ImproveAccuracy&Out-of-DistributionRobustness
Thissimple change not only improves accuracy but also significantly improves the quality of the predictive uncertainty estimation of Mixup in most cases under various forms of covariate shifts and out-of-distribution detection experiments.
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (0.69)