A General Divergence Modeling Strategy for Salient Object Detection
This addresses the subjective nature of saliency detection for computer vision applications, but it is incremental as it builds on existing ensemble and latent variable frameworks.
The paper tackles the problem of modeling predictive uncertainty in salient object detection by introducing a general divergence modeling strategy using multiple saliency annotations, which improves performance over existing deterministic and latent variable models.
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.