papers AI Learner
The Github is limit! Click to go to the new site.

Unsupervised Deep Tracking

2019-04-03
Ning Wang, Yibing Song, Chao Ma, Wengang Zhou, Wei Liu, Houqiang Li

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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1904.01828

PDF

https://arxiv.org/pdf/1904.01828


Similar Posts

Comments