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 | 52 | 9.51% |
| Quantization | 37 | 6.76% |
| Model Compression | 34 | 6.22% |
| Language Modelling | 27 | 4.94% |
| Image Classification | 26 | 4.75% |
| Federated Learning | 19 | 3.47% |
| Computational Efficiency | 16 | 2.93% |
| Question Answering | 11 | 2.01% |
| Retrieval | 8 | 1.46% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
