Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers

This paper improves state-of-the-art on-line trackers that use deep learning. Such trackers train a deep network to pick a specified object out from the background in an initial frame (initialization) and then keep training the model as tracking proceeds (updates). Our core contribution is a meta-learning-based method to adjust deep networks for tracking using off-line training. First, we learn initial parameters and per-parameter coefficients for fast online adaptation. Second, we use training signal from future frames for robustness to target appearance variations and environment changes. The resulting networks train significantly faster during the initialization, while improving robustness and accuracy. We demonstrate this approach on top of the current highest accuracy tracking approach, tracking-by-detection based MDNet and close competitor, the correlation-based CREST. Experimental results on both standard benchmarks, OTB and VOT2016, show improvements in speed, accuracy, and robustness on both trackers.