End-to-end weak supervision target detection method based on salient guidance

• Main Authors: GONG XIAOJIN, LAI BAISHENG
• Format: Patent
• Language: Chinese; English
• Published: 26.09.2017
• Subjects: CALCULATING; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses an end-to-end weak supervision target detection method based on salient guidance. According to the method, a deep neural network is constructed, and a salient sub-network of a target box is added on the basis of a weak supervised classifier network; meanwhile, seed target areas with related categories are selected according to the criterion of context difference by the aid of a category-related salient map trained with a weak supervision method, and the salient sub-network and a classifier sub-network are supervised and trained. Compared with existing weak supervision target detection methods, the method has the advantages that better performance is obtained, meanwhile, only training of image-grade labels is required, and the workload of training data labeling is reduced. 本发明公开了种基于显著性指导的端到端的弱监督目标检测方法。此方法构造个深度神经网络，在弱监督分类器网络的基础上增加目标框的显著性子网络；同时利用弱监督方法训练得到的类别相关的显著图，用上下文差异的准则选取类别相关的种子目标区域，用来监督训练显著性子网络和分类器子网络。本方法与以往的弱监督目标检测方法相比，得到了更好的性能，同时只需要图像级标签进行训练，减少了标注训练数据的工作量。