activity
20172020
most citedParadox in Deep Neural Networks: Similar yet Different while Different yet Similar

3 citations · 8 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CV20203 cited

Deep Neural Models for color discrimination and color constancy

Alban Flachot, Arash Akbarinia, Heiko H. Schütt +3

Color constancy is our ability to perceive constant colors across varying illuminations. Here, we trained deep neural networks to be color constant and evaluated their performance…

cs.CV20201 cited

The Utility of Decorrelating Colour Spaces in Vector Quantised Variational Autoencoders

Arash Akbarinia, Raquel Gil-Rodríguez, Alban Flachot +1

Vector quantised variational autoencoders (VQ-VAE) are characterised by three main components: 1) encoding visual data, 2) assigning different vectors in the so-called embeddin…

cs.CV20193 cited

Paradox in Deep Neural Networks: Similar yet Different while Different yet Similar

Arash Akbarinia, Karl R. Gegenfurtner

Machine learning is advancing towards a data-science approach, implying a necessity to a line of investigation to divulge the knowledge learnt by deep neuronal networks. Limiting t…

cs.CV20191 cited

Manifestation of Image Contrast in Deep Networks

Arash Akbarinia, Karl R. Gegenfurtner

Contrast is subject to dramatic changes across the visual field, depending on the source of light and scene configurations. Hence, the human visual system has evolved to be more se…

cs.CV2018

How is Contrast Encoded in Deep Neural Networks?

Arash Akbarinia, Karl R. Gegenfurtner

Contrast is a crucial factor in visual information processing. It is desired for a visual system - irrespective of being biological or artificial - to "perceive" the world robustly…

cs.CV2017

Colour Terms: a Categorisation Model Inspired by Visual Cortex Neurons

Arash Akbarinia, C. Alejandro Parraga

Although it seems counter-intuitive, categorical colours do not exist as external physical entities but are very much the product of our brains. Our cortical machinery segments the…