Instance Segmentation Models
SCNet
Introduced by Vu et al. in SCNet: Training Inference Sample Consistency for Instance SegmentationSample Consistency Network (SCNet) is a method for instance segmentation which ensures the IoU distribution of the samples at training time are as close to that at inference time. To this end, only the outputs of the last box stage are used for mask predictions at both training and inference. The Figure shows the IoU distribution of the samples going to the mask branch at training time with/without sample consistency compared to that at inference time.
Source: SCNet: Training Inference Sample Consistency for Instance Segmentation
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Music Source Separation | 1 | 12.50% |
| Cloth-Changing Person Re-Identification | 1 | 12.50% |
| Person Re-Identification | 1 | 12.50% |
| Image Enhancement | 1 | 12.50% |
| Vocal Bursts Type Prediction | 1 | 12.50% |
| Instance Segmentation | 1 | 12.50% |
| Object Detection | 1 | 12.50% |
| Semantic Segmentation | 1 | 12.50% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
