Salient Object Detection: A Benchmark

TL;DR

This paper benchmarks 40 state-of-the-art models for salient object detection across six datasets, highlighting recent progress, analyzing influencing factors, and proposing solutions for open challenges in the field.

Contribution

It provides a comprehensive comparison of models, analyzes key factors affecting performance, and suggests future research directions for salient object detection.

Findings

Rapid progress in accuracy and speed of models

Models designed specifically for salient detection outperform related models

Center bias and scene complexity significantly influence model performance

Abstract

We extensively compare, qualitatively and quantitatively, 40 state-of-the-art models (28 salient object detection, 10 fixation prediction, 1 objectness, and 1 baseline) over 6 challenging datasets for the purpose of benchmarking salient object detection and segmentation methods. From the results obtained so far, our evaluation shows a consistent rapid progress over the last few years in terms of both accuracy and running time. The top contenders in this benchmark significantly outperform the models identified as the best in the previous benchmark conducted just two years ago. We find that the models designed specifically for salient object detection generally work better than models in closely related areas, which in turn provides a precise definition and suggests an appropriate treatment of this problem that distinguishes it from other problems. In particular, we analyze the influences of center bias and scene complexity in model performance, which, along with the hard cases for state-of-the-art models, provide useful hints towards constructing more challenging large scale datasets and better saliency models. Finally, we propose probable solutions for tackling several open problems such as evaluation scores and dataset bias, which also suggest future research directions in the rapidly-growing field of salient object detection.