Iterative Saliency Enhancement using Superpixel Similarity

TL;DR

This paper introduces ISESS, a hybrid iterative method that enhances saliency maps by leveraging superpixel similarity, outperforming existing deep-learning models across multiple datasets.

Contribution

The paper presents a novel hybrid approach combining superpixel segmentation and saliency estimation in an iterative cycle for improved saliency detection.

Findings

Outperforms three state-of-the-art deep-learning methods on five datasets.

Effectively refines saliency maps through iterative superpixel similarity analysis.

Demonstrates consistent enhancement of saliency detection accuracy.

Abstract

Saliency Object Detection (SOD) has several applications in image analysis. The methods have evolved from image-intrinsic to object-inspired (deep-learning-based) models. When a model fail, however, there is no alternative to enhance its saliency map. We fill this gap by introducing a hybrid approach, named \textit{Iterative Saliency Enhancement over Superpixel Similarity} (ISESS), that iteratively generates enhanced saliency maps by executing two operations alternately: object-based superpixel segmentation and superpixel-based saliency estimation -- cycling operations never exploited. ISESS estimates seeds for superpixel delineation from a given saliency map and defines superpixel queries in the foreground and background. A new saliency map results from color similarities between queries and superpixels at each iteration. The process repeats and, after a given number of iterations, the generated saliency maps are combined into one by cellular automata. Finally, the resulting map is merged with the initial one by the maximum bewteen their average values per superpixel. We demonstrate that our hybrid model can consistently outperform three state-of-the-art deep-learning-based methods on five image datasets.