Efficient Visual Tracking with Exemplar Transformers
This addresses the need for efficient real-time visual tracking on standard hardware, though it is incremental as it builds on existing transformer architectures.
The paper tackles the problem of inefficient runtime in visual object tracking by introducing the Exemplar Transformer, a module that enables real-time tracking at 47 FPS on a CPU, which is up to 8x faster than other transformer-based models while outperforming lightweight trackers on multiple datasets.
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 https://github.com/pblatter/ettrack.