Circular Smooth Label (CSL) is a classification-based rotation detection technique for arbitrary-oriented object detection. It is used for circularly distributed angle classification and addresses the periodicity of the angle and increases the error tolerance to adjacent angles.
Source: On the Arbitrary-Oriented Object Detection: Classification based Approaches RevisitedPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Sign Language Recognition | 9 | 15.52% |
Self-Supervised Learning | 7 | 12.07% |
Sentence | 4 | 6.90% |
Person Re-Identification | 2 | 3.45% |
Causal Discovery | 2 | 3.45% |
Semantic Segmentation | 2 | 3.45% |
Sentence Embedding | 2 | 3.45% |
Image Classification | 2 | 3.45% |
Classification | 2 | 3.45% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |