Spatial-frequency biases in neurally aligned DCNNs emerge from human-like representations but do not primarily drive their adversarial robustness advantages.
Probing Human Visual Robustness with Neurally-Guided Deep Neural Networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
HVPNet introduces a Retinal Integration Module and cortical decoder to achieve strong accuracy-efficiency trade-offs on 22 datasets for seven salient and camouflaged object detection tasks across four modalities.
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.
-
HVPNet: A Bio-Inspired Network for General Salient and Camouflaged Object Detection
HVPNet introduces a Retinal Integration Module and cortical decoder to achieve strong accuracy-efficiency trade-offs on 22 datasets for seven salient and camouflaged object detection tasks across four modalities.