Towards a category-extended object detector with limited data
作者：
Highlights：
• Focusing on learning category-extended detector with limited data.
• Meeting the needs of real-world applications.
• Conflict-free loss leads to acceptable unified detectors in one training round.
• A well designed retraining phase further improve performance.
• Extensive experiments demonstrate the effectiveness of our method.
摘要
•Focusing on learning category-extended detector with limited data.•Meeting the needs of real-world applications.•Conflict-free loss leads to acceptable unified detectors in one training round.•A well designed retraining phase further improve performance.•Extensive experiments demonstrate the effectiveness of our method.
论文关键词：Object detector,Category-extended,Limited data,Multi-dataset
论文评审过程：Received 10 March 2022, Revised 17 June 2022, Accepted 25 July 2022, Available online 27 July 2022, Version of Record 2 August 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.108943
