Unsupervised Neural Architecture for Saliency Detection: Extended Version
This work addresses saliency detection for computer vision applications, but it appears incremental as it builds on existing neurophysiological insights without claiming major breakthroughs.
The authors tackled visual saliency detection by proposing a neural network architecture inspired by neurophysiology to simulate human selective attention, and results from a psychological experiment indicated good performance.
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.