论文标题
在线混合轻量级表示学习：其应用于视觉跟踪
Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking
论文作者
论文摘要
本文介绍了用于流数据的新型混合表示学习框架，其中视频中的图像框架由两个不同的深神经网络组成。一个是一个低位量化的网络，另一个是一个轻量级的全精度网络。前者以低成本学习粗略的主要信息，而后者则传达了剩余信息，以高保真对原始表示形式。提出的并行体系结构可有效地维护互补信息，因为可以在量化的网络中使用固定点算术，并且轻量级模型提供了紧凑的通道键入网络给出的精确表示。我们将混合表示技术纳入在线视觉跟踪任务中，其中深层神经网络需要实时处理目标外观的时间变化。与基于常规深层神经网络的最新实时跟踪器相比，我们的跟踪算法在标准基准测试中表现出竞争精度，其计算成本和内存足迹的一小部分。
This paper presents a novel hybrid representation learning framework for streaming data, where an image frame in a video is modeled by an ensemble of two distinct deep neural networks; one is a low-bit quantized network and the other is a lightweight full-precision network. The former learns coarse primary information with low cost while the latter conveys residual information for high fidelity to original representations. The proposed parallel architecture is effective to maintain complementary information since fixed-point arithmetic can be utilized in the quantized network and the lightweight model provides precise representations given by a compact channel-pruned network. We incorporate the hybrid representation technique into an online visual tracking task, where deep neural networks need to handle temporal variations of target appearances in real-time. Compared to the state-of-the-art real-time trackers based on conventional deep neural networks, our tracking algorithm demonstrates competitive accuracy on the standard benchmarks with a small fraction of computational cost and memory footprint.
