Network Pruning 벤치마크
Network Pruning on CIFAR-10
Accuracy
- 2019-05-23 — TAS-pruned ResNet-110: Accuracy 94.33
- 2026-06-10 — Finding Sparse Subnetworks in One Traini: Accuracy 95.12
| Rank | Model | Accuracy | GFLOPs | Inference Time (ms) | Paper | Code | Year |
|---|---|---|---|---|---|---|---|
| 1 | Finding Sparse Subnetworks in One Traini 자동 추출 | 95.12 | – | – | Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning | 2026 | |
| 2 | TAS-pruned ResNet-110 | 94.33 | 0.119 | – | Network Pruning via Transformable Architecture Search | D-X-Y/GDAS · D-X-Y/NAS-Projects · D-X-Y/AutoDL-Projects · +1 | 2019 |
| 3 | MobileNet – Quantised | – | – | 4.74 | Quantisation and Pruning for Neural Network Compression and Regularisation | kpaupamah/compression-and-regularisation | 2020 |
| 4 | AlexNet – Quantised | – | – | 5.23 | Quantisation and Pruning for Neural Network Compression and Regularisation | kpaupamah/compression-and-regularisation | 2020 |
| 5 | ShuffleNet – Quantised | – | – | 23.15 | Quantisation and Pruning for Neural Network Compression and Regularisation | kpaupamah/compression-and-regularisation | 2020 |
| 6 | A Hierarchical Importance-Guided Multi-o 자동 추출 | 51.9 | – | – | A Hierarchical Importance-Guided Multi-objective Evolutionary Framework for Deep Neural Network Pruning | 2026 |