Image Models
WideResNet
Introduced by Zagoruyko et al. in Wide Residual NetworksWide Residual Networks are a variant on ResNets where we decrease depth and increase the width of residual networks. This is achieved through the use of wide residual blocks.
Source: Wide Residual Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 20 | 22.22% |
| Out-of-Distribution Detection | 7 | 7.78% |
| Object Detection | 6 | 6.67% |
| Anomaly Detection | 5 | 5.56% |
| Adversarial Robustness | 5 | 5.56% |
| General Classification | 5 | 5.56% |
| Deep Learning | 3 | 3.33% |
| Model Compression | 3 | 3.33% |
| Sparse Learning | 2 | 2.22% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Global Average Pooling
|
Pooling Operations | |
Kaiming Initialization
|
Initialization | |
Wide Residual Block
|
Skip Connection Blocks |
