Wide 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 NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 20 | 25.97% |
Out-of-Distribution Detection | 6 | 7.79% |
Object Detection | 5 | 6.49% |
General Classification | 5 | 6.49% |
Anomaly Detection | 4 | 5.19% |
Adversarial Robustness | 4 | 5.19% |
Model Compression | 3 | 3.90% |
Sparse Learning | 2 | 2.60% |
Out of Distribution (OOD) Detection | 2 | 2.60% |
Component | Type |
|
---|---|---|
Global Average Pooling
|
Pooling Operations | |
Kaiming Initialization
|
Initialization | |
Wide Residual Block
|
Skip Connection Blocks |