Unsupervised Deep Tracking

Abstract

We propose an unsupervised visual tracking method in this paper. Different from existing approaches using extensive annotated data for supervised learning, our CNN model is trained on large-scale unlabeled videos in an unsupervised manner. Our motivation is that a robust tracker should be effective in both the forward and backward predictions (i.e., the tracker can forward localize the target object in successive frames and backtrace to its initial position in the first frame). We build our framework on a Siamese correlation filter network, which is trained using unlabeled raw videos. Meanwhile, we propose a multiple-frame validation method and a cost-sensitive loss to facilitate unsupervised learning. Without bells and whistles, the proposed unsupervised tracker achieves the baseline accuracy of fully supervised trackers, which require complete and accurate labels during training. Furthermore, unsupervised framework exhibits a potential in leveraging unlabeled or weakly labeled data to further improve the tracking accuracy.

to appear in CVPR 2019

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
• Multiple Object Tracking: A Literature Review
• A Novel Performance Evaluation Methodology for Single-Target Trackers
• DCFNet: Discriminant Correlation Filters Network for Visual Tracking
• Siamese Instance Search for Tracking
• A Twofold Siamese Network for Real-Time Object Tracking
• CREST: Convolutional Residual Learning for Visual Tracking
• VITAL: VIsual Tracking via Adversarial Learning
• TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
• YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video
• Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking
• Long-term Tracking in the Wild: A Benchmark
• End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning

Cited by in corpus (8)

• Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
• Do Different Tracking Tasks Require Different Appearance Models?
• Learning Video Object Segmentation from Unlabeled Videos
• Single-Camera Basketball Tracker through Pose and Semantic Feature Fusion
• Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning
• IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking
• ROAM: Recurrently Optimizing Tracking Model
• Keyfilter-Aware Real-Time UAV Object Tracking