MeMu: Metric correlation Siamese network and multi-class negative sampling for visual tracking
作者：
Highlights：
• A multi-class negative sampling method is proposed for Siamese network, which contains three kinds of negative samples with different amount of background information to better distinguish object and background.
• A metric correlation filter module is proposed to learn the filter that can better distinguish object and background through the multi-class negative samples.
• We present a Siamese network-based architecture to embed the metric correlation filter module mentioned above.
• The proposed tracking algorithm performs favorably against the state-of- the-art methods.
摘要
•A multi-class negative sampling method is proposed for Siamese network, which contains three kinds of negative samples with different amount of background information to better distinguish object and background.•A metric correlation filter module is proposed to learn the filter that can better distinguish object and background through the multi-class negative samples.•We present a Siamese network-based architecture to embed the metric correlation filter module mentioned above.•The proposed tracking algorithm performs favorably against the state-of- the-art methods.
论文关键词：Visual tracking,Siamese network,Metric correlation filter,Multi-class negative samples
论文评审过程：Received 15 April 2019, Revised 23 October 2019, Accepted 15 December 2019, Available online 24 December 2019, Version of Record 30 December 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.107170
