作者将DCF视为在Siamese网络中添加的相关滤波层,并通过将网络输出定义为跟踪目标位置的概率热图来推导反向传播。将特征提取网络和相关滤波网络一起进行端到端训练。
Abstract.
Discriminant Correlation Filters (DCF) based methods now become a kind of dominant approach to online object tracking.
基于DCF的跟踪方法已经成为一种主流的跟踪方法。
The features used in these methods, however, are either based on hand-crafted features like HoGs, or convolutional features trained independently from other tasks like image classification.
但是这类方法多采用手工特征(如HOG)或者在其他任务上(如图片分类)预训练的卷积特征。
In this work, we present an end-to-end lightweight network architecture, namely DCFNet, to learn the convolutional features and perform the correlation tracking process simultaneously.
本文作者提出了一种轻量级网络来学习