Model Compression
Pruning
Introduced by Li et al. in Pruning Filters for Efficient ConvNetsPapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Network Pruning | 71 | 12.03% |
| Model Compression | 46 | 7.80% |
| Quantization | 36 | 6.10% |
| Image Classification | 32 | 5.42% |
| Federated Learning | 21 | 3.56% |
| Language Modelling | 19 | 3.22% |
| Object Detection | 15 | 2.54% |
| Semantic Segmentation | 13 | 2.20% |
| Question Answering | 11 | 1.86% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
