Regularization
ScheduledDropPath
Introduced by Zoph et al. in Learning Transferable Architectures for Scalable Image RecognitionScheduledDropPath is a modified version of DropPath. In DropPath, each path in the cell is stochastically dropped with some fixed probability during training. In ScheduledDropPath, each path in the cell is dropped out with a probability that is linearly increased over the course of training.
Source: Learning Transferable Architectures for Scalable Image Recognition
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 2 | 50.00% |
| Evolutionary Algorithms | 1 | 25.00% |
| Classification | 1 | 25.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
