Discrepant multiple instance learning for weakly supervised object detection

Wei Gao

doi:10.1016/j.patcog.2021.108233

Discrepant multiple instance learning for weakly supervised object detection

2022-02-01

30

PRE

AI

DOI：10.1016/j.patcog.2021.108233

Original

Original request for help

Save

Abstract

En 中文

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. (c) 2021 Elsevier Ltd. All rights reserved.

Keywords:

Weakly supervised detection

Multiple instance learning

Learner discrepancy

Collaborative learning

Discrepant multiple instance learning for weakly supervised object detection

Abstract

Journal

Organization