Object Detection Models
RepPoints
Introduced by Yang et al. in RepPoints: Point Set Representation for Object DetectionRepPoints is a representation for object detection that consists of a set of points which indicate the spatial extent of an object and semantically significant local areas. This representation is learned via weak localization supervision from rectangular ground-truth boxes and implicit recognition feedback. Based on the richer RepPoints representation, the authors develop an anchor-free object detector that yields improved performance compared to using bounding boxes.
Source: RepPoints: Point Set Representation for Object Detection
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 9 | 47.37% |
| Object Detection In Aerial Images | 2 | 10.53% |
| Optical Character Recognition (OCR) | 1 | 5.26% |
| Model Compression | 1 | 5.26% |
| Cell Detection | 1 | 5.26% |
| Image Classification | 1 | 5.26% |
| Instance Segmentation | 1 | 5.26% |
| Object Localization | 1 | 5.26% |
| Philosophy | 1 | 5.26% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
