C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection
By Gao Yan, Boxiao Liu, Nan Guo, Xiaochun Ye, Fang Wan, Haihang You, Dongrui Fan. 2019
130 citations recorded by the source corpus.
Weakly supervised object detection (WSOD) that only needs image-level annotations has obtained much attention recently. By combining convolutional neural network with multiple instance learning method, Multiple Instance Detection Network (MIDN) has become the most popular method to address the WSOD problem and been adopted as the initial model in many works. We argue that MIDN inclines to converge to the most discriminative object parts, which limits the performance of methods based on it. In this paper, we propose a novel Coupled Multiple Instance Detection Network (C-MIDN) to address this problem. Specifically, we use a pair of MIDNs, which work in a complementary manner with proposal removal. The localization information of the MIDNs is further coupled to obtain tighter bounding boxes and localize multiple objects. We also introduce a Segmentation Guided Proposal Removal (SGPR) algorithm to guarantee the MIL constraint after the removal and ensure the robustness of C-MIDN. Through a simple implementation of the C-MIDN with online detector refinement, we obtain 53.6% and 50.3% mAP on the challenging PASCAL VOC 2007 and 2012 benchmarks respectively, which significantly outperform the previous state-of-the-arts.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Rui Wang
- Vignesh Ramanathan
- Dhruv Kumar Mahajan
- Luc Van Gool
- Yang Zou
- Dong Huang
- V. Bhagavatula
- Zeyi Huang
Citations in the corpus
- Weakly Supervised Object Localization and Detection: A Survey (2021, unknown): “The whole weakly supervised learning framework may be designed in a compact network model, such as in [46], [76], [101], [106], [117], [180], [182], [204], [219], [221], or contain several function-distinct DNN components, such as in [27], [98], [140], [160], [172], [193], [209].”
- Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection (2020, background): “[14] and [15] leverage segmentation maps to generate instance proposals with rich contextual information.”
- What leads to generalization of object proposals? (2020, background): “Object detection systems have shown considerable improvements for fully supervised settings [27,18,20,26,3], as well as weakly supervised settings [7,1,32] that only use image-level labels.”