Dynamic sample weighting for weakly supervised object detection
作者：
Highlights：
• A dynamic sample weighting strategy for weakly supervised object detection.
• Local domination is analyzed from the perspective of sample balance.
• A new perspective on sample importance is provided.
• Dynamically allocate the weights of positive and negative samples.
• Effectiveness and efficiency of the method are verified by sufficient experiments.
摘要
Highlights•A dynamic sample weighting strategy for weakly supervised object detection.•Local domination is analyzed from the perspective of sample balance.•A new perspective on sample importance is provided.•Dynamically allocate the weights of positive and negative samples.•Effectiveness and efficiency of the method are verified by sufficient experiments.
论文关键词：Weakly supervised learning,Object detection,Dynamic sample weighting,Multiple instance learning
论文评审过程：Received 28 October 2021, Revised 20 March 2022, Accepted 28 March 2022, Available online 31 March 2022, Version of Record 25 April 2022.
论文官网地址：https://doi.org/10.1016/j.imavis.2022.104444
