Network Pruning
Network Pruning is a popular approach to reduce a heavy network to obtain a light-weight form by removing redundancy in the heavy network. In this approach, a complex over-parameterized network is first trained, then pruned based on come criterions, and finally fine-tuned to achieve comparable performance with reduced parameters.
Source: Ensemble Knowledge Distillation for Learning Improved and Efficient Networks
Papers
Showing 1–10 of 534 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Feather | Top-1 Accuracy | 76.93 | — | Unverified |
| 2 | Spartan | Top-1 Accuracy | 76.17 | — | Unverified |
| 3 | ST-3 | Top-1 Accuracy | 76.03 | — | Unverified |
| 4 | AC/DC | Top-1 Accuracy | 75.64 | — | Unverified |
| 5 | CS | Top-1 Accuracy | 75.5 | — | Unverified |
| 6 | ProbMask | Top-1 Accuracy | 74.68 | — | Unverified |
| 7 | STR | Top-1 Accuracy | 74.31 | — | Unverified |
| 8 | DNW | Top-1 Accuracy | 74 | — | Unverified |
| 9 | GMP | Top-1 Accuracy | 73.91 | — | Unverified |