Energy-Based Generative Cooperative Saliency Prediction

TL;DR

This paper introduces a generative cooperative framework combining a latent variable model and an energy-based model for saliency prediction, capturing uncertainty and producing diverse, high-quality saliency maps.

Contribution

It proposes a novel coarse-to-fine cooperative approach with energy-based refinement, including a weakly supervised learning strategy and a refinement module for existing models.

Findings

Achieves state-of-the-art results in fully supervised saliency prediction.

Effectively models uncertainty and generates diverse saliency maps.

Improves weakly supervised saliency prediction performance.

Abstract

Conventional saliency prediction models typically learn a deterministic mapping from an image to its saliency map, and thus fail to explain the subjective nature of human attention. In this paper, to model the uncertainty of visual saliency, we study the saliency prediction problem from the perspective of generative models by learning a conditional probability distribution over the saliency map given an input image, and treating the saliency prediction as a sampling process from the learned distribution. Specifically, we propose a generative cooperative saliency prediction framework, where a conditional latent variable model (LVM) and a conditional energy-based model (EBM) are jointly trained to predict salient objects in a cooperative manner. The LVM serves as a fast but coarse predictor to efficiently produce an initial saliency map, which is then refined by the iterative Langevin revision of the EBM that serves as a slow but fine predictor. Such a coarse-to-fine cooperative saliency prediction strategy offers the best of both worlds. Moreover, we propose a "cooperative learning while recovering" strategy and apply it to weakly supervised saliency prediction, where saliency annotations of training images are partially observed. Lastly, we find that the learned energy function in the EBM can serve as a refinement module that can refine the results of other pre-trained saliency prediction models. Experimental results show that our model can produce a set of diverse and plausible saliency maps of an image, and obtain state-of-the-art performance in both fully supervised and weakly supervised saliency prediction tasks.