1 code implementation • 4 Dec 2021 • Xavier Soria, Angel Sappa, Patricio Humanante, Arash Akbarinia
It also generalizes well to other datasets without any fine-tuning.
Ranked #1 on Edge Detection on MDBD
no code implementations • 1 Jan 2021 • Arash Akbarinia, Raquel Gil-Rodriguez, Alban Flachot, Matteo Toscani
Our results show, with respect to the baseline network (whose input and output are RGB) 5-10% higher classification accuracy is obtained with decorrelating ColourConvNets.
1 code implementation • 28 Dec 2020 • Alban Flachot, Arash Akbarinia, Heiko H. Schütt, Roland W. Fleming, Felix A. Wichmann, Karl R. Gegenfurtner
High levels of color constancy were achieved with different DNN architectures.
1 code implementation • 30 Sep 2020 • Arash Akbarinia, Raquel Gil-Rodríguez, Alban Flachot, Matteo Toscani
We also observed that the learnt embedding space is easier to interpret in colour opponent models.
no code implementations • 12 Mar 2019 • 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.
no code implementations • 12 Feb 2019 • Arash Akbarinia, Karl R. Gegenfurtner
Contrast is subject to dramatic changes across the visual field, depending on the source of light and scene configurations.
no code implementations • 5 Sep 2018 • Arash Akbarinia, Karl R. Gegenfurtner
Contrast is a crucial factor in visual information processing.
no code implementations • 29 Nov 2017 • Arash Akbarinia, Raquel Gil Rodríguez, C. Alejandro Parraga
Our experiments on three colour constancy benchmark datasets suggest that previous results can significantly improve by adopting a contrast-variant-pooling mechanism.
no code implementations • 19 Sep 2017 • Arash Akbarinia, C. Alejandro Parraga
Although the neural substrate for this phenomenon is unknown, a recent study of cortical colour processing has discovered a set of neurons that are isoresponsive to stimuli in the shape of 3D-ellipsoidal surfaces in colour-opponent space.