Discrepant multiple instance learning for weakly supervised object detection
作者：
Highlights：
• We propose discrepant multiple instance learning (D-MIL), and target at enforcing weakly supervised object detection by localizing complementary instances with maximum completeness and minimum redundancy.
• We propose learner discrepancy and learner collaboration modules, and formulate a new “teachers-students” model with detection condence back for object localization.
• We achieve new state-of-the-art performance for weakly supervised object detection on MS-COCO dataset.
摘要
•We propose discrepant multiple instance learning (D-MIL), and target at enforcing weakly supervised object detection by localizing complementary instances with maximum completeness and minimum redundancy.•We propose learner discrepancy and learner collaboration modules, and formulate a new “teachers-students” model with detection condence back for object localization.•We achieve new state-of-the-art performance for weakly supervised object detection on MS-COCO dataset.
论文关键词：Weakly supervised detection,Multiple instance learning,Learner discrepancy,Collaborative learning
论文评审过程：Received 3 July 2020, Revised 22 June 2021, Accepted 6 August 2021, Available online 23 August 2021, Version of Record 9 September 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108233
