919 citations · 1.1k across the 7 of their papers we have counts for
7 papers
Spatial-frequency channels, shape bias, and adversarial robustness
Ajay Subramanian, Elena Sizikova, Najib J. Majaj +1
What spatial frequency information do humans and neural networks use to recognize objects? In neuroscience, critical band masking is an established tool that can reveal the frequen…
SATBench: Benchmarking the speed-accuracy tradeoff in object recognition by humans and dynamic neural networks
Ajay Subramanian, Sara Price, Omkar Kumbhar +3
The core of everyday tasks like reading and driving is active object recognition. Attempts to model such tasks are currently stymied by the inability to incorporate time. People sh…
Anytime Prediction as a Model of Human Reaction Time
Omkar Kumbhar, Elena Sizikova, Najib Majaj +1
Neural networks today often recognize objects as well as people do, and thus might serve as models of the human recognition process. However, most such networks provide their answe…
Using Human Psychophysics to Evaluate Generalization in Scene Text Recognition Models
Sahar Siddiqui, Elena Sizikova, Gemma Roig +2
Scene text recognition models have advanced greatly in recent years. Inspired by human reading we characterize two important scene text recognition models by measuring their domain…
Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs
Jonas Kubilius, Martin Schrimpf, Kohitij Kar +11
Deep convolutional artificial neural networks (ANNs) are the leading class of candidate models of the mechanisms of visual processing in the primate ventral stream. While initially…
Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition
Charles F. Cadieu, Ha Hong, Daniel L. K. Yamins +5
The primate visual system achieves remarkable visual object recognition performance even in brief presentations and under changes to object exemplar, geometric transformations, and…
The Neural Representation Benchmark and its Evaluation on Brain and Machine
Charles F. Cadieu, Ha Hong, Dan Yamins +3
A key requirement for the development of effective learning representations is their evaluation and comparison to representations we know to be effective. In natural sensory domain…