基于高斯差分特征网络的显著目标检测

Salient object detection based on difference of Gaussian feature network

中心-邻域对比度理论作为具有生理学依据的一种线索,在传统显著性检测模型中获得了广泛应用,然而该理论却很少显式地应用在基于深度卷积神经网络(CNN)的模型中。为了将经典的中心-邻域对比度理论引入深度卷积网络中,提出了一种基于高斯差分(Do G)特征网络的显著目标检测模型。首先通过在多个尺度的深度特征上构造高斯差分金字塔(DGP)结构以感知图像中显著目标的局部突出特性,进而用所得到的差分特征对语义信息丰富的深度特征进行加权选择,最终实现对显著目标的准确提取。进一步地,在提出的网络设计中采用标准的一维卷积来实现高斯平滑过程,从而在降低计算复杂度的同时实现了网络端到端的训练。通过把所提模型与六种显著目标检测算法在四个公用数据集上的实验结果进行对比,可知所提模型取得的结果在平均绝对误差(MAE)和最大F度量值的定量评价中均取得了最优表现,尤其是在DUTS-TE数据集上所提模型取得的结果的最大F度量值和平均绝对误差分别达到了0.885和0.039。实验结果表明,所提模型在复杂自然场景中对于显著目标具有良好的检测性能。

As a clue with physiological basis,the center-surround contrast theory has been widely used in traditional saliency detection models.However,this theory is rarely applied to models based on deep Convolutional Neural Network(CNN)explicitly.In order to introduce the classic center-surround contrast theory into deep CNN,a salient object detection model based on Difference of Gaussian(DoG)feature network was proposed.Firstly,a Difference of Gaussian Pyramid(DGP)structure was constructed on the deep features of multiple scales to perceive the local prominent features of salient object in an image.Then,the obtained differential feature were used to perform weighted selection to the deep features with rich semantic information.Finally,the accurate extraction of the salient object was realized.In addition,the Gaussian smoothing process was implemented by using standard one-dimensional convolution in the proposed network design,so as to reduce the computational complexity and realize the end-to-end training of the network at the same time.Through comparison of the proposed model and six salient object detection algorithms on four public datasets,it can be seen that the results obtained by the proposed model achieve the best performance in the quantitative evaluation of Mean Absolute Error(MAE)and maximum F-measure.Especially on the DUTS-TE dataset the maximum F-measure and the mean absolute error of the results of the proposed model reach 0.885 and 0.039 respectively.Experimental results show that the proposed model has good detection performance for salient objects in complex natural scenes.