RepPoints 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 DetectionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 9 | 45.00% |
Object Detection In Aerial Images | 2 | 10.00% |
Optical Character Recognition (OCR) | 1 | 5.00% |
Model Compression | 1 | 5.00% |
Cell Detection | 1 | 5.00% |
Image Classification | 1 | 5.00% |
Decoder | 1 | 5.00% |
Instance Segmentation | 1 | 5.00% |
Object Localization | 1 | 5.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |