Unsupervised Deep Tracking

TL;DR

This paper introduces an unsupervised deep learning approach for visual tracking that trains on unlabeled videos, achieving comparable accuracy to supervised methods and demonstrating potential for leveraging unlabeled data.

Contribution

It presents a novel unsupervised training framework for visual tracking using a Siamese correlation filter network with a multiple-frame validation and cost-sensitive loss.

Findings

Achieves baseline accuracy comparable to supervised trackers

Demonstrates effectiveness of unsupervised training on unlabeled videos

Shows potential for further improvement with more unlabeled data

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.