Add to ORKGSome recent artificial neural networks (ANNs) have claimed to model important aspects of primate neural and human performance data. Their demonstrated performance in object recognition is still dependent on exploiting low-level features for solving visual tasks in a way that humans do not. Out-of-distribution or adversarial input is challenging for ANNs. Humans instead learn abstract patterns and are mostly unaffected by certain extreme image distortions. We introduce a set of novel image transforms inspired by neurophysiological findings and evaluate humans and networks on an object recognition task. We show that machines perform better than humans for certain transforms and struggle to perform at par with humans on other transforms that a...
Quilty-Dunn et al. argue that DCNNs optimized for image classification exemplify structural disanalo...
Contains fulltext : 231147.pdf (Publisher’s version ) (Open Access)Inspired by cor...
Deep neural networks (DNNs) have recently been achieving state-of-the-art performance on a variety o...
Modern artificial neural networks, including convolutional neural networks and vision transformers, ...
We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object ...
Modern machine learning models for computer vision exceed humans in accuracy on specific visual reco...
Recent experiments in computer vision demonstrate texture bias as the primary reason for supreme res...
Deep Neural Networks (DNNs) have recently been put forward as computational models for feedforward p...
Deep neural networks have achieved state-of-the-art performance across a wide range of tasks. Convol...
Convolutional neural networks (CNNs) have been proposed as computational models for (rapid) human ob...
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasin...
The success of deep image classification networks has been met with enthusiasm and investment from b...
In a recent article, Guo et al. [arXiv:2206.11228] report that adversarially trained neural represen...
Neural Networks are prone to having lesser accuracy in the classification of images with noise pertu...
Although deep neural networks (DNNs) achieve excellent performance and even outperform humans on var...
Quilty-Dunn et al. argue that DCNNs optimized for image classification exemplify structural disanalo...
Contains fulltext : 231147.pdf (Publisher’s version ) (Open Access)Inspired by cor...
Deep neural networks (DNNs) have recently been achieving state-of-the-art performance on a variety o...
Modern artificial neural networks, including convolutional neural networks and vision transformers, ...
We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object ...
Modern machine learning models for computer vision exceed humans in accuracy on specific visual reco...
Recent experiments in computer vision demonstrate texture bias as the primary reason for supreme res...
Deep Neural Networks (DNNs) have recently been put forward as computational models for feedforward p...
Deep neural networks have achieved state-of-the-art performance across a wide range of tasks. Convol...
Convolutional neural networks (CNNs) have been proposed as computational models for (rapid) human ob...
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasin...
The success of deep image classification networks has been met with enthusiasm and investment from b...
In a recent article, Guo et al. [arXiv:2206.11228] report that adversarially trained neural represen...
Neural Networks are prone to having lesser accuracy in the classification of images with noise pertu...
Although deep neural networks (DNNs) achieve excellent performance and even outperform humans on var...
Quilty-Dunn et al. argue that DCNNs optimized for image classification exemplify structural disanalo...
Contains fulltext : 231147.pdf (Publisher’s version ) (Open Access)Inspired by cor...
Deep neural networks (DNNs) have recently been achieving state-of-the-art performance on a variety o...