Scalable logo detection by self co-learning

作者：

Highlights：

• The literature lacks large-scale logo detection test benchmarks due to rather expensive data selection and label annotation.

• We contribute a large-scale dataset collected automatically for scalable logo detection.

• We present a scalable logo detection solution characterised by joint co-learning and self-learning in a unified framework, without the tedious need for manually labelling any training data.

摘要

•The literature lacks large-scale logo detection test benchmarks due to rather expensive data selection and label annotation.•We contribute a large-scale dataset collected automatically for scalable logo detection.•We present a scalable logo detection solution characterised by joint co-learning and self-learning in a unified framework, without the tedious need for manually labelling any training data.

论文关键词：Object detection,Logo recognition,Logo dataset,Web data mining,Self-Learning,Co-Learning

论文评审过程：Received 1 April 2019, Revised 28 June 2019, Accepted 14 August 2019, Available online 28 August 2019, Version of Record 2 September 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107003