Showing 1–20 of 124 results
/ Date/ Name
Dec 24, 2019Big Transfer (BiT): General Visual Representation LearningMay 3, 2022Better plain ViT baselines for ImageNet-1kNov 15, 2021LiT: Zero-Shot Transfer with Locked-image text TuningJun 18, 2021How to train your ViT? Data, Augmentation, and Regularization in Vision TransformersMay 18, 2016Improving Weakly-Supervised Object Localization By Micro-AnnotationSep 17, 2024On weighted Blaschke--Santalo and strong Brascamp--Lieb inequalitiesDec 19, 2024Jet: A Modern Transformer-Based Normalizing FlowMar 19, 2016Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image SegmentationMar 27, 2014Closed-Form Training of Conditional Random Fields for Large Scale Image SegmentationDec 24, 2016PixelCNN Models with Auxiliary Variables for Natural Image ModelingApr 28, 2015Identifying Reliable Annotations for Large Scale Image SegmentationJul 5, 2018Detecting Visual Relationships Using Box AttentionJun 9, 2021Knowledge distillation: A good teacher is patient and consistentMay 20, 2022UViM: A Unified Modeling Approach for Vision with Learned Guiding CodesDec 15, 2022FlexiViT: One Model for All Patch SizesApr 14, 2016Remarks on curvature in the transportation metricMay 11, 2017Probabilistic Image ColorizationJul 7, 2010On Sobolev regularity of mass transport and transportation inequalitiesFeb 9, 2010On isoperimetric sets of radially symmetric measuresMar 28, 2013Optimal transportation of processes with infinite Kantorovich distance. Independence and symmetry