一种基于深度度量学习的视频分类方法

A Deep Metric Learning Based Video Classification Method

针对视频分类中普遍面临的类内离散度和类间相似性较大而制约分类性能的问题,该文提出一种基于深度度量学习的视频分类方法。该方法设计了一种深度网络,网络包含特征学习、基于深度度量学习的相似性度量,以及分类3个部分。其中相似性度量的工作原理为:首先,计算特征间的欧式距离作为样本之间的语义距离;其次,设计一个间隔分配函数,根据语义距离动态分配语义间隔;最后,根据样本语义间隔计算误差并反向传播,使网络能够学习到样本间语义距离的差异,自动聚焦于难分样本,以充分学习难分样本的特征。该网络在训练过程中采用多任务学习的方法,同时学习相似性度量和分类任务,以达到整体最优。在UCF101和HMDB51上的实验结果表明,与已有方法相比,提出的方法能有效提高视频分类精度。

To solve the common problem of classification variations and inter-class similarities in video classification performance restriction caused by big intra-class domain, this paper proposes a deep metric learning based video classification method. The proposed method designs a deep network which contains three parts： feature learning, deep metric learning based similarity measure as well as classification. The principle of similarity measure is： Firstly, the Euclidean distance between features is calculated as the semantic distance between samples. Secondly, a margin distributing function is designed to dynamically allocate margin in the basis of the semantic distances. Finally, the difference of the sample semantic distance can be learned by calculating the loss and propagating it backwards so as to the network can automatically focus on the hard negative samples and more fully learn the characteristic of them. With a multi-task learning training method in the training stage, the similarity measure and classification can be learned jointly. Experimental results on UCF101 and HMDB51 show that the proposed method can effectively improve the classification precision.