Salient Object Detection: A Survey

TL;DR

This survey comprehensively reviews recent advances in salient object detection, covering models, datasets, evaluation metrics, and open challenges, to provide a clear understanding of the field's progress and future directions.

Contribution

It offers an extensive overview of 228 publications, analyzing key concepts, techniques, datasets, and evaluation methods in salient object detection, highlighting open issues and future research directions.

Findings

Reviewed 228 publications on salient object detection

Identified key techniques and modeling trends

Discussed open problems like dataset bias and evaluation metrics

Abstract

Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision. While many models have been proposed and several applications have emerged, a deep understanding of achievements and issues remains lacking. We aim to provide a comprehensive review of recent progress in salient object detection and situate this field among other closely related areas such as generic scene segmentation, object proposal generation, and saliency for fixation prediction. Covering 228 publications, we survey i) roots, key concepts, and tasks, ii) core techniques and main modeling trends, and iii) datasets and evaluation metrics for salient object detection. We also discuss open problems such as evaluation metrics and dataset bias in model performance, and suggest future research directions.