Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Ari Morcos

Ari Morcos
Alert button

Objectives Matter: Understanding the Impact of Self-Supervised Objectives on Vision Transformer Representations


Apr 25, 2023
Shashank Shekhar, Florian Bordes, Pascal Vincent, Ari Morcos

Add code
Alert button


   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Stable and low-precision training for large-scale vision-language models


Apr 25, 2023
Mitchell Wortsman, Tim Dettmers, Luke Zettlemoyer, Ari Morcos, Ali Farhadi, Ludwig Schmidt

Add code
Alert button

Figure 1 for Stable and low-precision training for large-scale vision-language models
Figure 2 for Stable and low-precision training for large-scale vision-language models
Figure 3 for Stable and low-precision training for large-scale vision-language models
Figure 4 for Stable and low-precision training for large-scale vision-language models

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Cookbook of Self-Supervised Learning


Apr 24, 2023
Randall Balestriero, Mark Ibrahim, Vlad Sobal, Ari Morcos, Shashank Shekhar, Tom Goldstein, Florian Bordes, Adrien Bardes, Gregoire Mialon, Yuandong Tian, Avi Schwarzschild, Andrew Gordon Wilson, Jonas Geiping, Quentin Garrido, Pierre Fernandez, Amir Bar, Hamed Pirsiavash, Yann LeCun, Micah Goldblum

Add code
Alert button

Figure 1 for A Cookbook of Self-Supervised Learning
Figure 2 for A Cookbook of Self-Supervised Learning
Figure 3 for A Cookbook of Self-Supervised Learning
Figure 4 for A Cookbook of Self-Supervised Learning

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

The Robustness Limits of SoTA Vision Models to Natural Variation


Oct 24, 2022
Mark Ibrahim, Quentin Garrido, Ari Morcos, Diane Bouchacourt

Add code
Alert button

Figure 1 for The Robustness Limits of SoTA Vision Models to Natural Variation
Figure 2 for The Robustness Limits of SoTA Vision Models to Natural Variation
Figure 3 for The Robustness Limits of SoTA Vision Models to Natural Variation
Figure 4 for The Robustness Limits of SoTA Vision Models to Natural Variation

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Robust Self-Supervised Learning with Lie Groups


Oct 24, 2022
Mark Ibrahim, Diane Bouchacourt, Ari Morcos

Add code
Alert button

Figure 1 for Robust Self-Supervised Learning with Lie Groups
Figure 2 for Robust Self-Supervised Learning with Lie Groups
Figure 3 for Robust Self-Supervised Learning with Lie Groups
Figure 4 for Robust Self-Supervised Learning with Lie Groups

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Trade-offs of Local SGD at Scale: An Empirical Study


Oct 15, 2021
Jose Javier Gonzalez Ortiz, Jonathan Frankle, Mike Rabbat, Ari Morcos, Nicolas Ballas

Add code
Alert button

Figure 1 for Trade-offs of Local SGD at Scale: An Empirical Study
Figure 2 for Trade-offs of Local SGD at Scale: An Empirical Study
Figure 3 for Trade-offs of Local SGD at Scale: An Empirical Study
Figure 4 for Trade-offs of Local SGD at Scale: An Empirical Study

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Transformed CNNs: recasting pre-trained convolutional layers with self-attention


Jun 10, 2021
Stéphane d'Ascoli, Levent Sagun, Giulio Biroli, Ari Morcos

Add code
Alert button

Figure 1 for Transformed CNNs: recasting pre-trained convolutional layers with self-attention
Figure 2 for Transformed CNNs: recasting pre-trained convolutional layers with self-attention
Figure 3 for Transformed CNNs: recasting pre-trained convolutional layers with self-attention
Figure 4 for Transformed CNNs: recasting pre-trained convolutional layers with self-attention

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases


Mar 19, 2021
Stéphane d'Ascoli, Hugo Touvron, Matthew Leavitt, Ari Morcos, Giulio Biroli, Levent Sagun

Add code
Alert button

Figure 1 for ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Figure 2 for ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Figure 3 for ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Figure 4 for ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Towards falsifiable interpretability research


Oct 22, 2020
Matthew L. Leavitt, Ari Morcos

Add code
Alert button


   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Linking average- and worst-case perturbation robustness via class selectivity and dimensionality


Oct 14, 2020
Matthew L. Leavitt, Ari Morcos

Add code
Alert button

Figure 1 for Linking average- and worst-case perturbation robustness via class selectivity and dimensionality
Figure 2 for Linking average- and worst-case perturbation robustness via class selectivity and dimensionality
Figure 3 for Linking average- and worst-case perturbation robustness via class selectivity and dimensionality
Figure 4 for Linking average- and worst-case perturbation robustness via class selectivity and dimensionality
* arXiv admin note: text overlap with arXiv:2007.04440 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>