A Psychophysically Oriented Saliency Map Prediction Model

TL;DR

This paper introduces WECSF, a psychophysically inspired saliency prediction model that closely mimics human visual processing and outperforms existing models on various datasets, offering insights into primate vision mechanisms.

Contribution

The paper presents a novel saliency prediction architecture based on human visual cortex principles, integrating opponent color channels, wavelet transforms, and contrast sensitivity for improved accuracy.

Findings

WECSF outperforms state-of-the-art models on multiple datasets.

Fourier and spectral models excel on psychophysical synthetic images.

Deep neural networks require specific architectures for better psychophysical image prediction.

Abstract

Visual attention is one of the most significant characteristics for selecting and understanding the outside redundancy world. The human vision system cannot process all information simultaneously due to the visual information bottleneck. In order to reduce the redundant input of visual information, the human visual system mainly focuses on dominant parts of scenes. This is commonly known as visual saliency map prediction. This paper proposed a new psychophysical saliency prediction architecture, WECSF, inspired by multi-channel model of visual cortex functioning in humans. The model consists of opponent color channels, wavelet transform, wavelet energy map, and contrast sensitivity function for extracting low-level image features and providing a maximum approximation to the human visual system. The proposed model is evaluated using several datasets, including the MIT1003, MIT300, TORONTO, SID4VAM, and UCF Sports datasets. We also quantitatively and qualitatively compare the saliency prediction performance with that of other state-of-the-art models. Our model achieved strongly stable and better performance with different metrics on natural images, psychophysical synthetic images and dynamic videos. Additionally, we found that Fourier and spectral-inspired saliency prediction models outperformed other state-of-the-art non-neural network and even deep neural network models on psychophysical synthetic images. It can be explained and supported by the Fourier Vision Hypothesis. In the meantime, we suggest that deep neural networks need specific architectures and goals to be able to predict salient performance on psychophysical synthetic images better and more reliably. Finally, the proposed model could be used as a computational model of primate vision system and help us understand mechanism of primate vision system.