In some medical imaging tasks and other settings where only small parts of the image are
informative for the classification task, traditional CNNs can sometimes struggle to generalise …

Planting potatoes through plastic film with incomplete or excessive soil coverage over seed
holes significantly impairs yield. Existing covering methods rely solely on mechanical …

Saliency is the perceptual capacity of our visual system to focus our attention (ie gaze) on
relevant objects instead of the background. So far, computational methods for saliency …

Retinal prostheses are designed to aid individuals with retinal degenerative conditions such
as Retinitis Pigmentosa (RP) and Age-related Macular Degeneration (AMD). These …

In recent years, there has been rapid progress in computing performance and
communication techniques, leading to a surging interest in artificial intelligence. Artificial …

Processes occurring in brains, aka biological neural networks, can and have been modeled
within artificial neural network architectures. Due to this, we have conducted a review of …

Most of the saliency methods are evaluated on their ability to generate saliency maps, and
not on their functionality in a complete vision pipeline, like for instance, image classification …

Most of the saliency methods are evaluated for their ability to generate saliency maps, and
not for their functionality in a complete vision pipeline, for instance, image classification or …

Most of the saliency methods are evaluated on their ability to generate saliency maps, and
not on their functionality in a complete vision pipeline, like for instance, image classification …

Per als humans, el reconeixement d'objectes és un procés gairebé instantani, precís i
extremadament adaptable. A més, tenim la capacitat innata d'aprendre classes d'objectes …