Regularization
DropBlock
Introduced by Ghiasi et al. in DropBlock: A regularization method for convolutional networksDropBlock is a structured form of dropout directed at regularizing convolutional networks. In DropBlock, units in a contiguous region of a feature map are dropped together. As DropBlock discards features in a correlated area, the networks must look elsewhere for evidence to fit the data.
Source: DropBlock: A regularization method for convolutional networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 63 | 21.88% |
| Object | 33 | 11.46% |
| Real-Time Object Detection | 12 | 4.17% |
| Image Classification | 9 | 3.13% |
| Deep Learning | 8 | 2.78% |
| Person Re-Identification | 8 | 2.78% |
| Autonomous Driving | 7 | 2.43% |
| Semantic Segmentation | 7 | 2.43% |
| General Classification | 5 | 1.74% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
