A General Divergence Modeling Strategy for Salient Object Detection

TL;DR

This paper introduces a general divergence modeling strategy for salient object detection that leverages multiple annotations to better capture the subjective nature of saliency, improving prediction diversity and model performance.

Contribution

It proposes a novel divergence modeling approach using random sampling applicable to ensemble and latent variable models, enhancing saliency prediction diversity.

Findings

Superior performance demonstrated on benchmark datasets.

Effective modeling of subjective saliency variations.

Improved diversity in saliency predictions.

Abstract

Salient object detection is subjective in nature, which implies that multiple estimations should be related to the same input image. Most existing salient object detection models are deterministic following a point to point estimation learning pipeline, making them incapable of estimating the predictive distribution. Although latent variable model based stochastic prediction networks exist to model the prediction variants, the latent space based on the single clean saliency annotation is less reliable in exploring the subjective nature of saliency, leading to less effective saliency divergence modeling. Given multiple saliency annotations, we introduce a general divergence modeling strategy via random sampling, and apply our strategy to an ensemble based framework and three latent variable model based solutions to explore the subjective nature of saliency. Experimental results prove the superior performance of our general divergence modeling strategy.