The design of more complex and powerful neural network models has
significantly advanced the state-of-the-art in visual object tracking. These
advances can be attributed to deeper networks, or the introduction of new
building blocks, such as transformers. However, in the pursuit of increased
tracking performance, runtime is often hindered. Furthermore, efficient
tracking architectures have received surprisingly little attention. In this
paper, we introduce the Exemplar Transformer, a transformer module utilizing a
single instance level attention layer for realtime visual object tracking.
E.T.Track, our visual tracker that incorporates Exemplar Transformer modules,
runs at 47 FPS on a CPU. This is up to 8x faster than other transformer-based
models. When compared to lightweight trackers that can operate in realtime on
standard CPUs, E.T.Track consistently outperforms all other methods on the
LaSOT, OTB-100, NFS, TrackingNet, and VOT-ST2020 datasets. Code and models are
available at this https URL

本文介绍了一种利用单实例层级注意机制的 Transformer 模块，用于实时视觉物体跟踪的 Exemplar Transformer。通过将 Exemplar Transformer 模块应用于 E.T.Track 视觉追踪器，该方法在 CPU 上可实现 47FPS 的速度，比其他基于 Transformer 的模型快 8 倍以上，同时在 LaSOT，OTB-100，NFS，TrackingNet 和 VOT-ST2020 数据集上始终优于其他实时追踪器。