Skip Connection Blocks
Big-Little Module
Introduced by Chen et al. in Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech RecognitionBig-Little Modules are blocks for image models that have two branches: each of which represents a separate block from a deep model and a less deep counterpart. They were proposed as part of the BigLittle-Net architecture. The two branches are fused with a linear combination and unit weights. These two branches are known as Big-Branch (more layers and channels at low resolutions) and Little-Branch (fewer layers and channels at high resolution).
Source: Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 2 | 16.67% |
| Speech Synthesis | 1 | 8.33% |
| Text-To-Speech Synthesis | 1 | 8.33% |
| Fine-Grained Image Classification | 1 | 8.33% |
| Fine-Grained Visual Recognition | 1 | 8.33% |
| General Classification | 1 | 8.33% |
| Image Retrieval | 1 | 8.33% |
| Retrieval | 1 | 8.33% |
| Object | 1 | 8.33% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
1x1 Convolution
|
Convolutions | |
Convolution
|
Convolutions | |
Linear Layer
|
Feedforward Networks | |
Residual Connection
|
Skip Connections |
