AI Medical Compendium Journal:
Vision research

Showing 1 to 10 of 13 articles

Deep neural networks and image classification in biological vision.

Vision research
In this paper we consider recent advances in the use of deep convolutional neural networks to understanding biological vision. We focus on claims about the plausibility of feedforward deep convolutional neural networks (fDCNNs) as models of image cla...

A failure to learn object shape geometry: Implications for convolutional neural networks as plausible models of biological vision.

Vision research
Here we examine the plausibility of deep convolutional neural networks (CNNs) as a theoretical framework for understanding biological vision in the context of image classification. Recent work on object recognition in human vision has shown that both...

Color for object recognition: Hue and chroma sensitivity in the deep features of convolutional neural networks.

Vision research
In this work, we examined the color tuning of units in the hidden layers of AlexNet, VGG-16 and VGG-19 convolutional neural networks and their relevance for the successful recognition of an object. We first selected the patches for which the units ar...

3D shape estimation in a constraint optimization neural network.

Vision research
One of the most important aspects of visual perception is the inference of 3D shape from a 2D retinal image of the outside world. The existence of several valid mapping functions from object to data makes this inverse problem ill-posed and therefore ...

Are there any 'object detectors' in the hidden layers of CNNs trained to identify objects or scenes?

Vision research
Various methods of measuring unit selectivity have been developed with the aim of better understanding how neural networks work. But the different measures provide divergent estimates of selectivity, and this has led to different conclusions regardin...

Hiding a plane with a pixel: examining shape-bias in CNNs and the benefit of building in biological constraints.

Vision research
When deep convolutional neural networks (CNNs) are trained "end-to-end" on raw data, some of the feature detectors they develop in their early layers resemble the representations found in early visual cortex. This result has been used to draw paralle...

Deciphering image contrast in object classification deep networks.

Vision research
The ultimate goal of neuroscience is to explain how complex behaviour arises from neuronal activity. A comparable level of complexity also emerges in deep neural networks (DNNs) while exhibiting human-level performance in demanding visual tasks. Unli...

Local features and global shape information in object classification by deep convolutional neural networks.

Vision research
Deep convolutional neural networks (DCNNs) show impressive similarities to the human visual system. Recent research, however, suggests that DCNNs have limitations in recognizing objects by their shape. We tested the hypothesis that DCNNs are sensitiv...

Time-resolved correspondences between deep neural network layers and EEG measurements in object processing.

Vision research
The ventral visual stream is known to be organized hierarchically, where early visual areas processing simplistic features feed into higher visual areas processing more complex features. Hierarchical convolutional neural networks (CNNs) were largely ...