Progressive Multi-Stage Learning for Discriminative Tracking
This addresses sample selection challenges in visual tracking, an incremental improvement for computer vision applications.
The paper tackles the problem of selecting high-quality training samples for online model adaptation in visual tracking by proposing a progressive multi-stage learning scheme with time-weighted, detection-guided self-paced learning. Experiments on benchmark datasets demonstrate the effectiveness of the framework.
Visual tracking is typically solved as a discriminative learning problem that usually requires high-quality samples for online model adaptation. It is a critical and challenging problem to evaluate the training samples collected from previous predictions and employ sample selection by their quality to train the model. To tackle the above problem, we propose a joint discriminative learning scheme with the progressive multi-stage optimization policy of sample selection for robust visual tracking. The proposed scheme presents a novel time-weighted and detection-guided self-paced learning strategy for easy-to-hard sample selection, which is capable of tolerating relatively large intra-class variations while maintaining inter-class separability. Such a self-paced learning strategy is jointly optimized in conjunction with the discriminative tracking process, resulting in robust tracking results. Experiments on the benchmark datasets demonstrate the effectiveness of the proposed learning framework.