Visual Search

Retinotopy improves the categorisation and localisation of visual objects in CNNs

as was presented at the 32nd International Conference on Artificial Neural Networks (ICANN 2023) in Heraklion (Greece).

this proceedings paper follows up the poster presented in :
Jean-Nicolas Jérémie, Emmanuel Daucé, Laurent U Perrinet (2023). Retinotopy improves the categorisation and localisation of visual objects in CNNs. In preparation.
Cite URL
Jean-Nicolas Jérémie, Emmanuel Daucé, Laurent U Perrinet
PDF Cite DOI URL

Retinotopy improves the categorisation and localisation of visual objects in CNNs

Retinotopy improves the categorisation and localisation of visual objects in CNNs

as was presented at the Computational Cognitive Neuroscience Society Meeting 2023 in Oxford

see a follow-up presentation in:
Jean-Nicolas Jérémie, Emmanuel Daucé, Laurent U Perrinet (2023). Retinotopy improves the categorisation and localisation of visual objects in CNNs. 32nd International Conference on Artificial Neural Networks (ICANN 2023).
PDF Cite DOI URL
Jean-Nicolas Jérémie, Emmanuel Daucé, Laurent U Perrinet
Cite URL

Ultra-rapid visual search in natural images using active deep learning

This work extends to natural scenes a previous work on visual search on a simplified task formulated in
Emmanuel Daucé, Pierre Albigès, Laurent U Perrinet (2020). A dual foveal-peripheral visual processing model implements efficient saccade selection. Journal of Vision.
Cite DOI Pdf Code URL bioRxiv
Jean-Nicolas Jérémie, Emmanuel Daucé, Laurent U Perrinet
Cite URL

Ultra-rapid visual search in natural images using active deep learning

Visual search, that is, the simultaneous localization and detection of a visual target of interest, is a vital task. Applied to the …

Jean-Nicolas Jérémie, Emmanuel Daucé, Laurent U Perrinet

Retinotopic mapping improves the reliability of image classification