So we leverage weakly supervised semantic segmentation method to generate the segmenta- tion map, and introduce the segmentation cover rate as a metric to guide�...

The localization information of the MIDNs is further coupled to obtain tighter bounding boxes and localize multiple objects. We also introduce a Segmentation�...

A novel Coupled Multiple Instance Detection Network (C-MIDN) is proposed, which uses a pair of MIDNs, which work in a complementary manner with proposal�...

By combining convolutional neural network with multiple instance learning method, Multiple Instance Detection Network (MIDN) has become the most popular method�...

C-MIDN [10] introduces a method for coupling proposals to prevent the detector from capturing the most discriminative object part rather than the whole object.

[C-MIDN] C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection. [ICCV 2019] [ pdf ]; Towards�...

C-MIDN+FRCNN. 50.3. C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection. 2019. 5. Pred Net (�...

C-midn: Coupled multiple instance detection network with segmentation guidance for weakly supervised object detection. Y Gao, B Liu, N Guo, X Ye, F Wan, H�...

14. C-MIDN. 53.6. C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection ; 15. FRCNN C-MIL. 53.1.

Wan, H. You, and D. Fan "C-MIDN: Coupled multiple instance detection network with segmentation guidance for weakly supervised object detection", in ICCV 2019.