One-Stage Object Detection Models
Contour Proposal Network
Introduced by Upschulte et al. in Contour Proposal Networks for Biomedical Instance SegmentationThe 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 Segmentation
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Semantic Segmentation | 3 | 16.67% |
| Weakly-Supervised Semantic Segmentation | 2 | 11.11% |
| Few-Shot Learning | 1 | 5.56% |
| Unsupervised Few-Shot Image Classification | 1 | 5.56% |
| Unsupervised Few-Shot Learning | 1 | 5.56% |
| 3D Human Pose Estimation | 1 | 5.56% |
| Denoising | 1 | 5.56% |
| Monocular 3D Human Pose Estimation | 1 | 5.56% |
| Pose Estimation | 1 | 5.56% |
Convolution
Non Maximum Suppression
