Real-Time Object Tracking via Meta-Learning: Efficient Model Adaptation and One-Shot Channel Pruning

We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few gradient-descent iterations during tracking while pruning its network channels using the target ground-truth at the first frame. Such a learning problem is formulated as a meta-learning task, where a meta-tracker is trained by updating its meta-parameters for initial weights, learning rates, and pruning masks through carefully designed tracking simulations. The integrated metatracker greatly improves tracking performance by accelerating the convergence of online learning and reducing the cost of feature computation. Experimental evaluation on the standard datasets demonstrates its outstanding accuracy and speed compared to the state-of-the-art methods. Introduction Recent advances in deep neural networks have drastically improved visual object tracking technology. By learning strong representations of target and background using convolutional neural networks, many algorithms (