YOLOv3和双线性特征融合的细粒度图像分类  

Fine-grained classification based on bilinear feature fusion and YOLOv3

作　　者：闫子旭 侯志强 熊磊 刘晓义 余旺盛[3] 马素刚 Yan Zixu;Hou Zhiqiang;Xiong Lei;Liu Xiaoyi;Yu Wangsheng;Ma Sugang(College of Computer,Xi′an University of Posts and Telecommunications,Xi′an 710121,China;College of Telecommunications,Xi′an Jiaotong University,Xi′an 710049,China;College of Information and Navigation,Air Force Engineering University,Xi′an 710077,China)

机构地区：[1]西安邮电大学计算机学院,西安710121 [2]西安交通大学电信学院,西安710049 [3]空军工程大学信息与导航学院,西安710077

出　　处：《中国图象图形学报》2021年第4期847-856,共10页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61703423,61473309,61379104)。

摘　　要：目的细粒度图像分类是计算机视觉领域具有挑战性的课题,目的是将一个大的类别分为更详细的子类别,在工业和学术方面都有着十分广泛的研究需求。为了改善细粒度图像分类过程中不相关背景干扰和类别差异特征难以提取的问题,提出了一种将目标检测方法 YOLOv3(you only look once)和双线性融合网络相结合的细粒度分类优化算法,以此提高细粒度图像分类的性能。方法利用重新训练过的目标检测算法YOLOv3粗略确定目标在图像中的位置;使用背景抑制方法消除目标以外的信息干扰;利用融合不同通道、不同层级卷积层特征的方法对经典的细粒度分类算法双线性卷积神经网络(bilinear convolutional neural network,B-CNN)进行改进,优化分类性能,通过融合双线性网络中不同卷积层的特征向量,得到更加丰富的互补信息,从而提高细粒度分类精度。结果实验结果表明,在CUB-200-2011 (Caltech-UCSD Birds-200-2011)、Cars196和Aircrafts100数据集中,本文算法的分类准确率分别为86.3%、92.8%和89.0%,比经典的B-CNN细粒度分类算法分别提高了2.2%、1.5%和4.9%,验证了本文算法的有效性。同时,与已有细粒度图像分类算法相比也表现出一定的优势。结论改进算法使用YOLOv3有效滤除了大量无关背景,通过特征融合方法来改进双线性卷积神经分类网络,丰富特征信息,使分类的结果更加精准。Objective Image classification is a classic topic in the field of computer vision. It can be divided into coarsegrained classification and fine-grained classification. The purpose of coarse-grained classification is to identify objects of different categories, whereas that of fine-grained image classification is to subdivide larger categories into more fine-grained categories, which in many cases have greater use value. Fine-grained image classification is a challenging research topic in computer vision. There are extensive research needs and application scenarios of fine-grained image classification in the industry and academia. Due to background interference and difficulty in extracting effective classification features, problems still exist in fine-grained classification. Compared with general image classification, fine-grained classification experiences background interference. This problem can be addressed by object detection methods. The task of object detection is to find the objects of interest in the image and determine their position and size. At present, more and more target detection methods are based on deep learning. These methods can be divided into two categories: one-stage detection method and twostage detection method. One-stage detection method has fast detection speed, but its accuracy is slightly lower. Examples of one-stage detection method mainly include you only look once(YOLO) and single shot multibox detector(SSD). Twostage detection method first uses region recommendation to generate candidate targets, and then it uses a convolutional neural network(CNN) to process this condition. Some of the examples of this method include R-CNN(region CNN), SPPNET(spatial pyramid pooling convolutional network), and Faster R-CNN. Among them, YOLOv3 of the YOLO series has achieved a better balance in detection accuracy and speed compared with other commonly used target detection frameworks.Method To improve the accuracy of these detection methods, a fine-grained classification algorithm based on the fus

关 键 词：细粒度图像分类 目标检测 背景抑制 特征融合 双线性卷积神经网络(B-CNN) 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]