Tracking-by-Trackers with a Distilled and Reinforced Model

8 Jul 2020  ·  Matteo Dunnhofer, Niki Martinel, Christian Micheloni ·

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.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Visual Object Tracking GOT-10k TRASFUST Average Overlap 61.7 # 26
Success Rate 0.5 72.9 # 20
Visual Object Tracking LaSOT TRASFUST AUC 57.6 # 28
Visual Object Tracking OTB-2015 TRASFUST Precision 0.931 # 1
AUC 0.701 # 5
Visual Object Tracking UAV123 TRASFUST AUC 0.679 # 9
Precision 0.873 # 4

Methods