基于显著图的弱监督实时目标检测  

Weakly Supervised Real-time Object Detection Based on Saliency Map

作　　者：李阳[1] 王璞 刘扬[1] 刘国军[1] 王春宇[1] 刘晓燕[1] 郭茂祖[1,2,3] LI Yang;WANG Pu;LIU Yang;LIU Guo-Jun;WANG Chun-Yu;LIU Xiao-Yan;GUO Mao-Zu(School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001;School of Electrical and Information Engineering,Beijing University of Civil Engineering and Architecture,Beijing 100044;Beijing Key Laboratory of Intelligent Processing for Building Big Data,Beijing 100044)

机构地区：[1]哈尔滨工业大学计算机科学与技术学院,哈尔滨150001 [2]北京建筑大学电气与信息工程学院,北京100044 [3]建筑大数据智能处理方法研究北京重点实验室,北京100044

出　　处：《自动化学报》2020年第2期242-255,共14页Acta Automatica Sinica

基　　金：国家重点基础研究发展计划(2016YFC0901902);国家自然科学基金(61671188,61571164,61976071,61871020)资助~~

摘　　要：深度卷积神经网络(Deep convolutional neural network,DCNN)在目标检测任务上使用目标的全标注来训练网络参数,其检测准确率也得到了大幅度的提升.然而,获取目标的边界框(Bounding-box)标注是一项耗时且代价高的工作.此外,目标检测的实时性是制约其实用性的另一个重要问题.为了克服这两个问题,本文提出一种基于图像级标注的弱监督实时目标检测方法.该方法分为三个子模块:1)首先应用分类网络和反向传递过程生成类别显著图,该显著图提供了目标在图像中的位置信息;2)根据类别显著图生成目标的伪标注(Pseudo-bounding-box);3)最后将伪标注看作真实标注并优化实时目标检测网络的参数.不同于其他弱监督目标检测方法,本文方法无需目标候选集合获取过程,并且对于测试图像仅通过网络的前向传递过程就可以获取检测结果,因此极大地加快了检测的速率(实时性).此外,该方法简单易用;针对未知类别的目标检测,只需要训练目标类别的分类网络和检测网络.因此本框架具有较强的泛化能力,为解决弱监督实时检测问题提供了新的研究思路.在PASCAL VOC 2007数据集上的实验表明:1)本文方法在检测的准确率上取得了较好的提升;2)实现了弱监督条件下的实时检测.Deep convolutional neural network(DCNN)trains model parameters by using object bounding-box annotations in object detection task,and its detection accuracy has been greatly improved.However,bounding-box annotations are very expensive and time-consuming.In addition,the real-time performance of object detection is another important problem that restricts its practicality.To solve these two problems,this paper proposes a new weakly supervised real-time object detector with image-level labels.The proposed method includes three sub-modules:1)firstly,producing class-specific saliency maps based on a classification network and the back-propagation process,which provides object localization clues;2)then,generating pseudo-annotations(pseudo-bounding-box)based on class-specific saliency maps;3)finally,treating the pseudo annotations as ground-truth and optimizing the parameters of our real-time object detection network.Different from other weakly supervised object detection methods,our method avoids the computing process for obtaining object candidates.And we obtain object detection results of test images by feed-forward process,thus our method greatly speeds up the detection process(real-time).In addition,our method is simple and easy to use;for unknown class objects,we only need to train the classification and detection networks.So our method has a strong generalization ability and provides a new idea for weakly supervision real-time detection problem.Extensive experiments on PASCAL VOC 2007 benchmark show that:1)the proposed method achieves a good improvement on detection accuracy;2)it realizes real-time detection under weakly supervised condition.

关 键 词：弱监督 实时目标检测 显著图 伪标注 深度卷积神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]