Deep Meta Learning for Real-Time Target-Aware Visual Tracking
This addresses the computational bottleneck in visual tracking for applications requiring fast processing, though it is incremental as it builds on existing Siamese and meta-learning methods.
The paper tackles the problem of real-time visual tracking by eliminating the need for continuous re-training of classifiers or filters, achieving competitive performance at real-time speeds.
In this paper, we propose a novel on-line visual tracking framework based on the Siamese matching network and meta-learner network, which run at real-time speeds. Conventional deep convolutional feature-based discriminative visual tracking algorithms require continuous re-training of classifiers or correlation filters, which involve solving complex optimization tasks to adapt to the new appearance of a target object. To alleviate this complex process, our proposed algorithm incorporates and utilizes a meta-learner network to provide the matching network with new appearance information of the target objects by adding target-aware feature space. The parameters for the target-specific feature space are provided instantly from a single forward-pass of the meta-learner network. By eliminating the necessity of continuously solving complex optimization tasks in the course of tracking, experimental results demonstrate that our algorithm performs at a real-time speed while maintaining competitive performance among other state-of-the-art tracking algorithms.