Discrepant multiple instance learning for weakly supervised object detection

•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. Multiple Instance Learning (MIL) is a fundamental method for weakly supervised object detection (WSOD), but experiences difficulty in excluding local optimal solutions and may miss objects or falsely localize object parts. In this paper, we introduce discrepantly collaborative modules into MIL and thereby create discrepant multiple instance learning (D-MIL), pursuing optimal solutions in a simple-yet-effective way. D-MIL adopts multiple MIL learners to pursue discrepant yet complementary solutions indicating object parts, which are fused with a collaboration module for precise object localization. D-MIL implements a new “teachers-students” model, where MIL learners act as “teachers” and object detectors as “students”. Multiple teachers provide rich yet complementary information, which are absorbed by students and transferred back to reinforce the performance of teachers. Experiments show that D-MIL significantly improves the baseline while achieves state-of-the-art performance on the challenging MS-COCO object detection benchmark.