Object Detection Models
Libra R-CNN
Introduced by Pang et al. in Libra R-CNN: Towards Balanced Learning for Object DetectionLibra R-CNN is an object detection model that seeks to achieve a balanced training procedure. The authors motivation is that training in past detectors has suffered from imbalance during the training process, which generally consists in three levels – sample level, feature level, and objective level. To mitigate the adverse effects, Libra R-CNN integrates three novel components: IoU-balanced sampling, balanced feature pyramid, and balanced L1 loss, respectively for reducing the imbalance at sample, feature, and objective level.
Source: Libra R-CNN: Towards Balanced Learning for Object Detection
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 2 | 40.00% |
| Ensemble Learning | 1 | 20.00% |
| Medical Object Detection | 1 | 20.00% |
| Object Localization | 1 | 20.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Balanced Feature Pyramid
|
Feature Pyramid Blocks | |
Balanced L1 Loss
|
Loss Functions | |
IoU-Balanced Sampling
|
Prioritized Sampling |
