Spatial-frequency biases in neurally aligned DCNNs emerge from human-like representations but do not primarily drive their adversarial robustness advantages.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.NC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dissociating spatial frequency reliance from adversarial robustness advantages in neurally guided deep convolutional neural networks
Spatial-frequency biases in neurally aligned DCNNs emerge from human-like representations but do not primarily drive their adversarial robustness advantages.