A General Divergence Modeling Strategy for Salient Object Detection

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.

arXiv commentCode is available at: https://npucvr.github.io/Divergence_SOD/

References in corpus (9)

• Auto-Encoding Variational Bayes
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• U${}^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection
• Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
• Conditional Variational Image Deraining
• Alternating Back-Propagation for Generator Network
• Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels
• Dense Uncertainty Estimation