全局模型和局部优化的深度网络显著性检测

Deep Network Saliency Detection Based on Global Model and Local Optimization

设计有效的特征向量是显著性检测方法的关键,决定了模型效果的上限,基于深度卷积神经网络和手工提取特征相结合的思路,提出了一种新的基于全局模型和局部搜索的显著性检测方法。在全局模型中,通过对VGG-16网络设计额外的卷积层进行训练,生成初始显著图,达到了从图像整体角度预测每一个候选区域显著性的目的。在局部优化模型中,设计区域对比度描述子和区域特征描述子对多级分割的超像素点进行描述,预测每一个区域的显著性值。最后,利用线性拟合的方法将两种模型中产生的显著图进行融合,得到最终的显著图。对4个数据集进行对比测试实验,实验结果表明,本文方法具有最高的准确率。

The design of the effective feature vectors is the key to the saliency detection algorithm, which determines the upper bound of the model effect. A new saliency detection algorithm based on global model and local search is proposed by combining the deep convolution neural networks and the hand-crafted features. In the global model, the initial saliency map is generated from designing the extra convolution layers for VGG-16 network training, and thus the saliency value of each object candidate region can be predicted from a global perspective. In local optimization model, the super-pixel region with multi-degree segmentation is described by designing the contrast descriptors and region characteristic descriptors, and the saliency score of each region is predicted. Finally, a linear fitting method is used to fuse the result generated from two models, and the final saliency map is obtained. Contrast experiments for four data sets are demonstrated and the results show that the proposed algorithm has the highest precision.