The Contour Proposal Network (CPN) detects possibly overlapping objects in an image while simultaneously fitting pixel-precise closed object contours. The CPN can incorporate state of the art object detection architectures as backbone networks into a fast single-stage instance segmentation model that can be trained end-to-end.
Source: Contour Proposal Networks for Biomedical Instance SegmentationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
3D Human Pose Estimation | 3 | 9.09% |
Monocular 3D Human Pose Estimation | 3 | 9.09% |
Pose Estimation | 3 | 9.09% |
Semantic Segmentation | 3 | 9.09% |
Cell Segmentation | 2 | 6.06% |
Instance Segmentation | 2 | 6.06% |
Object Detection | 2 | 6.06% |
Weakly-Supervised Semantic Segmentation | 2 | 6.06% |
Scene Text Detection | 1 | 3.03% |