VITAL: VIsual Tracking via Adversarial Learning

Yibing Song, Chao Ma, Xiaohe Wu, Lijun Gong, Linchao Bao, Wangmeng Zuo, Chunhua Shen, Rynson W.H. Lau, Ming-Hsuan Yang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 8990-8999


The tracking-by-detection framework consists of two stages, i.e., drawing samples around the target object in the first stage and classifying each sample as the target object or as background in the second stage. The performance of existing tracking-by-detection trackers using deep classification networks is limited by two aspects. First, the positive samples in each frame are highly spatially overlapped, and they fail to capture rich appearance variations. Second, there exists severe class imbalance between positive and negative samples. This paper presents the VITAL algorithm to address these two problems via adversarial learning. To augment positive samples, we use a generative network to randomly generate masks, which are applied to input features to capture a variety of appearance changes. With the use of adversarial learning, our network identifies the mask that maintains the most robust features of the target objects over a long temporal span. In addition, to handle the issue of class imbalance, we propose a high-order cost sensitive loss to decrease the effect of easy negative samples to facilitate training the classification network. Extensive experiments on benchmark datasets demonstrate that the proposed tracker performs favorably against state-of-the-art approaches.

Related Material

[pdf] [arXiv]
author = {Song, Yibing and Ma, Chao and Wu, Xiaohe and Gong, Lijun and Bao, Linchao and Zuo, Wangmeng and Shen, Chunhua and Lau, Rynson W.H. and Yang, Ming-Hsuan},
title = {VITAL: VIsual Tracking via Adversarial Learning},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}