Unsupervised Neural Architecture for Saliency Detection: Extended Version

11/18/2014
by   Natalia Efremova, et al.
0

We propose a novel neural network architecture for visual saliency detections, which utilizes neurophysiologically plausible mechanisms for extraction of salient regions. The model has been significantly inspired by recent findings from neurophysiology and aimed to simulate the bottom-up processes of human selective attention. Two types of features were analyzed: color and direction of maximum variance. The mechanism we employ for processing those features is PCA, implemented by means of normalized Hebbian learning and the waves of spikes. To evaluate performance of our model we have conducted psychological experiment. Comparison of simulation results with those of experiment indicates good performance of our model.

READ FULL TEXT

page 2

page 5

page 6

research
07/22/2013

Is Bottom-Up Attention Useful for Scene Recognition?

The human visual system employs a selective attention mechanism to under...
research
07/22/2013

A study of parameters affecting visual saliency assessment

Since the early 2000s, computational visual saliency has been a very act...
research
11/15/2018

A Neurodynamical model of Saliency prediction in V1

Computations in the primary visual cortex (area V1 or striate cortex) ha...
research
11/08/2020

An HVS-Oriented Saliency Map Prediction Modeling

Visual attention is one of the most significant characteristics for sele...
research
01/23/2018

Revisiting Video Saliency: A Large-scale Benchmark and a New Model

In this work, we contribute to video saliency research in two ways. Firs...
research
09/05/2021

Deep Saliency Prior for Reducing Visual Distraction

Using only a model that was trained to predict where people look at imag...

Please sign up or login with your details

Forgot password? Click here to reset