Release the Power of Online-Training for Robust Visual Tracking

Authors

  • Yifan Yang UCAS
  • Guorong Li UCAS
  • Yuankai Qi Harbin Institute of Technology
  • QIngming Huang UCAS

DOI:

https://doi.org/10.1609/aaai.v34i07.6956

Abstract

Convolutional neural networks (CNNs) have been widely adopted in the visual tracking community, significantly improving the state-of-the-art. However, most of them ignore the important cues lying in the distribution of training data and high-level features that are tightly coupled with the target/background classification. In this paper, we propose to improve the tracking accuracy via online training. On the one hand, we squeeze redundant training data by analyzing the dataset distribution in low-level feature space. On the other hand, we design statistic-based losses to increase the inter-class distance while decreasing the intra-class variance of high-level semantic features. We demonstrate the effectiveness on top of two high-performance tracking methods: MDNet and DAT. Experimental results on the challenging large-scale OTB2015 and UAVDT demonstrate the outstanding performance of our tracking method.

Downloads

Published

2020-04-03

How to Cite

Yang, Y., Li, G., Qi, Y., & Huang, Q. (2020). Release the Power of Online-Training for Robust Visual Tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 12645-12652. https://doi.org/10.1609/aaai.v34i07.6956

Issue

Section

AAAI Technical Track: Vision