Multi-scale Visual Attention & Saliency Modelling with Decision Theory

TL;DR

This paper introduces a multi-scale discriminant saliency model using decision theory, wavelet transforms, and Hidden Markov Trees to improve visual saliency detection, validated on eye-tracking data.

Contribution

It proposes a novel multi-scale saliency framework combining wavelet analysis and HMT, enhancing the accuracy of saliency maps over existing methods.

Findings

MDIS maps outperform AIM in quantitative evaluations

Multi-scale approach captures saliency more effectively across different window sizes

Simulations provide insights for future research directions

Abstract

Bottom-up saliency, an early human visual processing, behaves like binary classification of interest and null hypothesis. Its discriminant power, mutual information of image features and class distribution, is closely related to saliency value by the well-known centre-surround theory. As classification accuracy very much depends on window sizes, the discriminant saliency (power) varies according to sampling scales. Discriminating power estimation in multi-scales framework needs integrating with wavelet transformation and then estimating statistical discrepancy of two consecutive scales (centre-surround windows) by Hidden Markov Tree (HMT) model. Finally, multi-scale discriminant saliency (MDIS) maps are combined by the maximum information rule to synthesize a final saliency map. All MDIS maps are evaluated with standard quantitative tools (NSS,LCC,AUC) on N.Bruce's database with ground truth data as eye-tracking locations ; as well assessed qualitatively by visual examination of individual cases. For evaluating MDIS against well-known AIM saliency method, simulations are needed and described in details with several interesting conclusions, drawn for further research directions.