Tracking-by-Trackers with a Distilled and Reinforced Model
This work addresses the problem of efficient and accurate visual object tracking for computer vision applications, presenting an incremental improvement by combining existing techniques.
The paper tackles visual object tracking by unifying fast processing, online adaptation, and tracker fusion into a single student model trained via knowledge distillation and reinforcement learning, achieving competitive performance with real-time state-of-the-art trackers.
Visual object tracking was generally tackled by reasoning independently on fast processing algorithms, accurate online adaptation methods, and fusion of trackers. In this paper, we unify such goals by proposing a novel tracking methodology that takes advantage of other visual trackers, offline and online. A compact student model is trained via the marriage of knowledge distillation and reinforcement learning. The first allows to transfer and compress tracking knowledge of other trackers. The second enables the learning of evaluation measures which are then exploited online. After learning, the student can be ultimately used to build (i) a very fast single-shot tracker, (ii) a tracker with a simple and effective online adaptation mechanism, (iii) a tracker that performs fusion of other trackers. Extensive validation shows that the proposed algorithms compete with real-time state-of-the-art trackers.