activity
20182024
most citedGlobal Explanations of Neural Networks: Mapping the Landscape of Predictions

20 citations · 58 across the 14 of their papers we have counts for

collaborators
Showing 2023Show all

6 papers · 1 filter

cs.LG2023

Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations

Cian Eastwood, Julius von Kügelgen, Linus Ericsson +4

Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown…

cs.LG2023

Discovering environments with XRM

Mohammad Pezeshki, Diane Bouchacourt, Mark Ibrahim +3

Environment annotations are essential for the success of many out-of-distribution (OOD) generalization methods. Unfortunately, these are costly to obtain and often limited by human…

cs.CV20234 cited

PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning

Florian Bordes, Shashank Shekhar, Mark Ibrahim +3

Synthetic image datasets offer unmatched advantages for designing and evaluating deep neural networks: they make it possible to (i) render as many data samples as needed, (ii) prec…

cs.CV2023

Does Progress On Object Recognition Benchmarks Improve Real-World Generalization?

Megan Richards, Polina Kirichenko, Diane Bouchacourt +1

For more than a decade, researchers have measured progress in object recognition on ImageNet-based generalization benchmarks such as ImageNet-A, -C, and -R. Recent advances in foun…

cs.CV20232 cited

Pinpointing Why Object Recognition Performance Degrades Across Income Levels and Geographies

Laura Gustafson, Megan Richards, Melissa Hall +3

Despite impressive advances in object-recognition, deep learning systems' performance degrades significantly across geographies and lower income levels raising pressing concerns of…

cs.LG2023

A Cookbook of Self-Supervised Learning

Randall Balestriero, Mark Ibrahim, Vlad Sobal +16

Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning. Yet, much like cooking, training SSL methods is a delicate art wi…