Manifestation of image contrast in deep networks

A Akbarinia, KR Gegenfurtner - arXiv preprint arXiv:1902.04378, 2019 - arxiv.org
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 …

How is Contrast Encoded in Deep Neural Networks?

A Akbarinia, KR Gegenfurtner - arXiv preprint arXiv:1809.01438, 2018 - arxiv.org
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 under large …

[HTML][HTML] Deciphering image contrast in object classification deep networks

A Akbarinia, R Gil-Rodriguez - Vision Research, 2020 - Elsevier
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) …

Learning dual transformation networks for image contrast enhancement

Y Zhu, X Fu, A Liu - IEEE Signal Processing Letters, 2020 - ieeexplore.ieee.org
In this work, we introduce a dual transformation network for single image contrast
enhancement, which usually aims to improve global contrast and enrich local details. To this …

Do contrast measures correlate? a pilot investigation

SA Amirshahi, A Kadyrova… - 2019 8th European …, 2019 - ieeexplore.ieee.org
Different issues related to contrast has been investigated in image processing and computer
vision. This has made introducing an accurate contrast measure an important issue. While …

Contrast sensitivity function in deep networks

A Akbarinia, Y Morgenstern, KR Gegenfurtner - Neural Networks, 2023 - Elsevier
The contrast sensitivity function (CSF) is a fundamental signature of the visual system that
has been measured extensively in several species. It is defined by the visibility threshold for …

Perceptnet: A human visual system inspired neural network for estimating perceptual distance

A Hepburn, V Laparra, J Malo… - … on Image Processing …, 2020 - ieeexplore.ieee.org
Traditionally, the vision community has devised algorithms to estimate the distance between
an original image and images that have been subject to perturbations. Inspiration was …

Locally adaptive contrast enhancement using convolutional neural network

BG Han, HS Yang, YS Moon - 2018 IEEE International …, 2018 - ieeexplore.ieee.org
Law contrast images obtained from smart phones or any imaging devices are difficult to
process by image processing systems and general users. Therefore, an enhancement of low …

A framework for contrast enhancement algorithms optimization

S Zini, M Buzzelli, S Bianco… - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
We present a general-purpose framework for the optimization of parametric contrast
enhancement algorithms. We first define a regression module for image acceptability, which …

A Robust Contrast Learning Method Based on Semantic Enhancement

J Guo, J An, Y Yu, A Liu, Y Liu - 2023 5th International …, 2023 - ieeexplore.ieee.org
Recent self-supervised contrast learning methods have made significant progress in the
field of computer vision, and these methods aim to learn useful feature representations from …