Image Model Blocks
FBNet Block
Introduced by Wu et al. in FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture SearchFBNet Block is an image model block used in the FBNet architectures discovered through DNAS neural architecture search. The basic building blocks employed are depthwise convolutions and a residual connection.
Source: FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 3 | 18.75% |
| Semantic Segmentation | 2 | 12.50% |
| Meta-Learning | 1 | 6.25% |
| Point Cloud Completion | 1 | 6.25% |
| Autonomous Driving | 1 | 6.25% |
| Image Segmentation | 1 | 6.25% |
| Scene Segmentation | 1 | 6.25% |
| Quantization | 1 | 6.25% |
| Depth Estimation | 1 | 6.25% |
1x1 Convolution
Depthwise Convolution
Grouped Convolution
Pointwise Convolution
ReLU
Residual Connection
