The DiCarlo Lab at MIT

Dapello, Joel

2022
Dapello, Joel
Kar, Kohitij
Schrimpf, Martin
Geary, Robert
Ferguson, Michael
Cox, David D.
DiCarlo, James J.
Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness

In:
bioRxiv

Available At:
https://www.biorxiv.org/content/10.1101/2022.07.01.498495v1.full.pdf

Abstract: Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness
2022
Guo, Chong
Lee, Michael J.
Leclerc, Guillaume
Dapello, Joel
Rao, Yug
Madry, Aleksander
DiCarlo, James J.
Adversarially trained neural representations may already be as robust as corresponding biological neural representations

In:
arXiv

Available At:
https://arxiv.org/abs/2206.11228v1

Download file

Abstract: Adversarially trained neural representations may already be as robust as corresponding biological neural representations
2021
Baidya, Avinash
Dapello, Joel
DiCarlo, James J.
Marques, Tiago
Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs

In:
Shared Visual Representations in Human & Machine Intelligence – NeurIPS Workshop

Available At:
https://arxiv.org/abs/2110.10645

Download file

Abstract: Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs
2020
Dapello, Joel
Marques, Tiago
Schrimpf, Martin
Geiger, Franziska
Cox, David D.
DiCarlo, James J.
Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations

In:
Neural Information Processing Systems (NeurIPS; spotlight)

Available At:
https://www.biorxiv.org/content/10.1101/2020.06.16.154542v27

Download file

Abstract: Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations