ProMIS:概率图采样图像增广驱动的弱监督物体检测方法  

ProMIS:probability-based multi-object image synthesis-relevant weakly supervised object detection method

作　　者：李笑颜 阚美娜 梁浩 山世光[1,2,3] Li Xiaoyan;Kan Meina;Liang Hao;Shan Shiguang(Key Laboratory of Intelligent Information Processing,Chinese Academy of Sciences,Beijing 100190,China;School of Computer Science and Technology,University of Chinese Academy of Sciences,Beijing 100049,China;Peng Cheng Laboratory,Shenzhen 518055,China)

机构地区：[1]中国科学院智能信息处理重点实验室,北京100190 [2]中国科学院大学计算机科学与技术学院,北京100049 [3]鹏城实验室,深圳518055

出　　处：《中国图象图形学报》2023年第7期2037-2053,共17页Journal of Image and Graphics

基　　金：国家重点研发计划资助(2017YFA0700800);国家自然科学基金项目(62122074,62176251);北京市科技新星项目(Z191100001119123)。

摘　　要：目的弱监督物体检测是一种仅利用图像类别标签训练物体检测器的技术。近年来弱监督物体检测器的精度不断提高,但在如何提升检出物体的完整性、如何从多个同类物体中区分出单一个体的问题上仍面临极大挑战。围绕上述问题,提出了基于物体布局后验概率图进行多物体图像增广的弱监督物体检测方法ProMIS(probability-based multi-object image synthesis)。方法将检出物体存储到物体候选池,并将候选池中的物体插入到输入图像中,构造带有伪边界框标注的增广图像,进而利用增广后的图像训练弱监督物体检测器。该方法包含图像增广与弱监督物体检测两个相互作用的模块。图像增广模块将候选池中的物体插入一幅输入图像,该过程通过后验概率的估计与采样对插入物体的类别、位置和尺度进行约束,以保证增广图像的合理性;弱监督物体检测模块利用增广后的多物体图像、对应的类别标签、物体伪边界框标签训练物体检测器,并将原始输入图像上检到的高置信度物体储存到物体候选池中。训练过程中,为了避免过拟合,本文在基线算法的基础上增加一个并行的检测分支,即基于增广边界框的检测分支,该分支利用增广得到的伪边界框标注进行训练,原有基线算法的检测分支仍使用图像标签进行训练。测试时,本文方法仅使用基于增广边界框的检测分支产生检测结果。本文提出的增广策略和检测器的分支结构在不同弱监督物体检测器上均适用。结果在Pascal VOC(pattern analysis,statistical modeling and computational learning visual object classes)2007和Pascal VOC 2012数据集上,将该方法嵌入到多种现有的弱监督物体检测器中,平均精度均值(mean average precision,mAP)平均获得了2.9%和4.2%的提升。结论本文证明了采用弱监督物体检测伪边界框标签生成的增广图像包含丰富信息,能够辅助弱监督�Objective Neural networks based fully supervised object detectors can be an essential way to improve the performance of object detection,and it is more reliable for real-world applications to a certain extent.However,it is still challenging for annotating huge amounts of data.A bounding box-related labor-intensive labeling task is required to be resolved for multiple categories and application scenarios.To meet multiple real-world applications,it is challenging to collect largescale detection training datasets as well.Thus,a weakly supervised object detector is designed for its optimization through image category annotations only.Recent weakly supervised object detectors are focused on the multi-instance learning(MIL)technique.In these methods,object proposals are classified and aggregated into an image classification result,and objects are detected by selecting the bounding box that contributes most to the aggregated image classification results among all object proposals.However,since weakly supervised object detection lacks instance-level annotations,a challenging issue of differentiation needs to be resolved for instance from a part of the instance or a cluster of multiple instances of the same category.For training the object detector,our method proposed is focused on the learning ability to distinguish instances by inserting high confidence-relevant detected objects into an input image and generating augmented images along with pseudo bounding box annotations.However,the naive random augmentation method can not immediately improve the detection performance,owing to the following reasons:1)over-fitting:the generated data is used to train the detection head itself;2)infeasible augmentation:spatial distribution of the generated objects is often quite heterogenous from the real data since the hyper-parameters of the insertion are all sampled from uniform distributions.Method To resolve these issues mentioned above,a probability-based multi-object image synthesis(ProMIS)relevant weakly supervised object detectio

关 键 词：弱监督物体检测 多物体数据增广 图像融合 概率图采样 后验概率估计 

分 类 号：TP391.6[自动化与计算机技术—计算机应用技术]