Context-aware Deep Feature Compression for High-speed Visual Tracking
This addresses the need for real-time visual tracking in applications like surveillance or robotics, though it is incremental as it builds on existing correlation filter frameworks.
The paper tackles the problem of achieving high-speed visual tracking with state-of-the-art performance by proposing a context-aware deep feature compression method, resulting in a tracking speed of over 100 fps while maintaining comparable accuracy to slower trackers.
We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in the proposed deep feature compression that is achieved by a context-aware scheme utilizing multiple expert auto-encoders; a context in our framework refers to the coarse category of the tracking target according to appearance patterns. In the pre-training phase, one expert auto-encoder is trained per category. In the tracking phase, the best expert auto-encoder is selected for a given target, and only this auto-encoder is used. To achieve high tracking performance with the compressed feature map, we introduce extrinsic denoising processes and a new orthogonality loss term for pre-training and fine-tuning of the expert auto-encoders. We validate the proposed context-aware framework through a number of experiments, where our method achieves a comparable performance to state-of-the-art trackers which cannot run in real-time, while running at a significantly fast speed of over 100 fps.