Josip Djolonga

Publications by Year

Research Areas

Domain Adaptation and Few-Shot Learning, Multimodal Machine Learning Applications, Advanced Neural Network Applications, Machine Learning and Algorithms, Human Pose and Action Recognition

Most-Cited Works

• → On Mutual Information Maximization for Representation Learning(2019)219 cited
• → A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark(2019)160 cited
• → Scaling Vision Transformers to 22 Billion Parameters(2023)118 cited
• High-Dimensional Gaussian Process Bandits(2013)
• → Revisiting the Calibration of Modern Neural Networks(2021)69 cited
• From MAP to Marginals: Variational Inference in Bayesian Submodular Models(2014)
• You Only Train Once: Loss-Conditional Training of Deep Networks(2020)
• Differentiable Learning of Submodular Models(2017)
• The Visual Task Adaptation Benchmark(2019)