Image Model Blocks
Compact Global Descriptor
Introduced by He et al. in Compact Global Descriptor for Neural NetworksA Compact Global Descriptor is an image model block for modelling interactions between positions across different dimensions (e.g., channels, frames). This descriptor enables subsequent convolutions to access the informative global features. It is a form of attention.
Source: Compact Global Descriptor for Neural Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Audio Classification | 1 | 25.00% |
| Deep Attention | 1 | 25.00% |
| Image Classification | 1 | 25.00% |
| Object Detection | 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 |
