activity
20212023
most citedAdversarially trained neural representations may already be as robust as corresponding biological neural representations

19 citations · 27 across the 4 of their papers we have counts for

collaborators
Showing 2021 · eess.IVShow all

1 paper · 2 filters

eess.IV2021

Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs

Avinash Baidya, Joel Dapello, James J. DiCarlo +1

While some convolutional neural networks (CNNs) have surpassed human visual abilities in object classification, they often struggle to recognize objects in images corrupted with di…