Adversarial Semi-Supervised Multi-Domain Tracking
This addresses the challenge of building robust visual trackers for unseen videos, though it appears incremental as it builds on existing multi-domain learning methods.
The paper tackles the problem of poor generalization in multi-domain visual trackers by proposing a semi-supervised scheme that separates domain-invariant and domain-specific features using adversarial learning, resulting in a tracker that performs exceptionally on different video types.
Neural networks for multi-domain learning empowers an effective combination of information from different domains by sharing and co-learning the parameters. In visual tracking, the emerging features in shared layers of a multi-domain tracker, trained on various sequences, are crucial for tracking in unseen videos. Yet, in a fully shared architecture, some of the emerging features are useful only in a specific domain, reducing the generalization of the learned feature representation. We propose a semi-supervised learning scheme to separate domain-invariant and domain-specific features using adversarial learning, to encourage mutual exclusion between them, and to leverage self-supervised learning for enhancing the shared features using the unlabeled reservoir. By employing these features and training dedicated layers for each sequence, we build a tracker that performs exceptionally on different types of videos.