Tracking Emerges by Colorizing Videos
This work addresses the challenge of self-supervised visual tracking for computer vision applications, offering a novel approach that reduces reliance on labeled data.
The paper tackles the problem of learning visual tracking without manual supervision by training a model to colorize grayscale videos using a reference frame, which results in the model automatically learning to track visual regions and outperforming optical flow-based methods.
We use large amounts of unlabeled video to learn models for visual tracking without manual human supervision. We leverage the natural temporal coherency of color to create a model that learns to colorize gray-scale videos by copying colors from a reference frame. Quantitative and qualitative experiments suggest that this task causes the model to automatically learn to track visual regions. Although the model is trained without any ground-truth labels, our method learns to track well enough to outperform the latest methods based on optical flow. Moreover, our results suggest that failures to track are correlated with failures to colorize, indicating that advancing video colorization may further improve self-supervised visual tracking.