activity
20172021
most citedA Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark

160 citations · 739 across the 18 of their papers we have counts for

collaborators

38 papers

cs.CV20212 cited

SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size

Jessica Yung, Rob Romijnders, Alexander Kolesnikov +6

Before deploying machine learning models it is critical to assess their robustness. In the context of deep neural networks for image understanding, changing the object location, ro…

cs.LG20218 cited

Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark

Vincent Dumoulin, Neil Houlsby, Utku Evci +4

Meta and transfer learning are two successful families of approaches to few-shot learning. Despite highly related goals, state-of-the-art advances in each family are measured large…

cs.LG202021 cited

A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation

Francesco Locatello, Stefan Bauer, Mario Lucic +4

The idea behind the \emph{unsupervised} learning of \emph{disentangled} representations is that real-world data is generated by a few explanatory factors of variation which can be…

cs.LG202026 cited

Scalable Transfer Learning with Expert Models

Joan Puigcerver, Carlos Riquelme, Basil Mustafa +5

Transfer of pre-trained representations can improve sample efficiency and reduce computational requirements for new tasks. However, representations used for transfer are usually ge…

cs.LG20202 cited

A Commentary on the Unsupervised Learning of Disentangled Representations

Francesco Locatello, Stefan Bauer, Mario Lucic +4

The goal of the unsupervised learning of disentangled representations is to separate the independent explanatory factors of variation in the data without access to supervision. In…

cs.CV2020

On Robustness and Transferability of Convolutional Neural Networks

Josip Djolonga, Jessica Yung, Michael Tschannen +11

Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts. However, several recent breakthroughs in transfer learning suggest…