Grounding inductive biases in natural images:invariance stems from variations in data

9 June 2021

Papers citing "Grounding inductive biases in natural images:invariance stems from variations in data"

9 / 9 papers shown

Title
What Affects Learned Equivariance in Deep Image Recognition Models? Robert-Jan Bruintjes Tomasz Motyka J. C. V. Gemert 18 7 0 05 Apr 2023
The Robustness Limits of SoTA Vision Models to Natural Variation Mark Ibrahim Q. Garrido Ari S. Morcos Diane Bouchacourt VLM 35 16 0 24 Oct 2022
Robust Self-Supervised Learning with Lie Groups Mark Ibrahim Diane Bouchacourt Ari S. Morcos SSL OOD 33 6 0 24 Oct 2022
The Lie Derivative for Measuring Learned Equivariance Nate Gruver Marc Finzi Micah Goldblum A. Wilson 16 34 0 06 Oct 2022
Regularising for invariance to data augmentation improves supervised learning Aleksander Botev Matthias Bauer Soham De 30 14 0 07 Mar 2022
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision Priya Goyal Quentin Duval Isaac Seessel Mathilde Caron Ishan Misra Levent Sagun Armand Joulin Piotr Bojanowski VLM SSL 26 110 0 16 Feb 2022
Deep invariant networks with differentiable augmentation layers Cédric Rommel Thomas Moreau Alexandre Gramfort OOD 17 8 0 04 Feb 2022
Weakly-Supervised Disentanglement Without Compromises Francesco Locatello Ben Poole Gunnar Rätsch Bernhard Schölkopf Olivier Bachem Michael Tschannen CoGe OOD DRL 175 313 0 07 Feb 2020
A General Theory of Equivariant CNNs on Homogeneous Spaces Taco S. Cohen Mario Geiger Maurice Weiler MLT AI4CE 151 308 0 05 Nov 2018