SOTAVerified

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 401425 of 534 papers

TitleStatusHype
Composition of Saliency Metrics for Channel Pruning with a Myopic Oracle0
How Not to Give a FLOP: Combining Regularization and Pruning for Efficient InferenceCode1
DHP: Differentiable Meta Pruning via HyperNetworksCode1
Understanding the Effects of Data Parallelism and Sparsity on Neural Network Training0
Similarity of Neural Networks with GradientsCode1
Graph Attention Network based Pruning for Reconstructing 3D Liver Vessel Morphology from Contrasted CT Images0
Verification of Neural Networks: Enhancing Scalability through Pruning0
What is the State of Neural Network Pruning?Code1
Adaptive Neural Connections for Sparsity Learning0
Comparing Rewinding and Fine-tuning in Neural Network PruningCode1
Joint Device-Edge Inference over Wireless Links with Pruning0
Privacy-preserving Learning via Deep Net Pruning0
Good Subnetworks Provably Exist: Pruning via Greedy Forward SelectionCode1
HRank: Filter Pruning using High-Rank Feature MapCode1
HYDRA: Pruning Adversarially Robust Neural NetworksCode1
On the Decision Boundaries of Neural Networks: A Tropical Geometry Perspective0
Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs0
Structured Sparsification with Joint Optimization of Group Convolution and Channel ShuffleCode0
Knapsack Pruning with Inner DistillationCode1
Picking Winning Tickets Before Training by Preserving Gradient FlowCode1
Network Pruning via Annealing and Direct Sparsity Control0
Convolutional Neural Network Pruning Using Filter Attenuation0
Soft Threshold Weight Reparameterization for Learnable SparsityCode1
Activation Density driven Energy-Efficient Pruning in Training0
Progressive Local Filter Pruning for Image Retrieval Acceleration0
Show:102550
← PrevPage 17 of 22Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50-2.3 GFLOPsAccuracy78.79Unverified
2ResNet50-1.5 GFLOPsAccuracy78.07Unverified
3ResNet50 2.5 GFLOPSAccuracy78Unverified
4RegX-1.6GAccuracy77.97Unverified
5ResNet50 2.0 GFLOPSAccuracy77.7Unverified
6ResNet50-3G FLOPsAccuracy77.1Unverified
7ResNet50-2G FLOPsAccuracy76.4Unverified
8ResNet50-1G FLOPsAccuracy76.38Unverified
9TAS-pruned ResNet-50Accuracy76.2Unverified
10ResNet50Accuracy75.59Unverified
#ModelMetricClaimedVerifiedStatus
1FeatherTop-1 Accuracy76.93Unverified
2SpartanTop-1 Accuracy76.17Unverified
3ST-3Top-1 Accuracy76.03Unverified
4AC/DCTop-1 Accuracy75.64Unverified
5CSTop-1 Accuracy75.5Unverified
6ProbMaskTop-1 Accuracy74.68Unverified
7STRTop-1 Accuracy74.31Unverified
8DNWTop-1 Accuracy74Unverified
9GMPTop-1 Accuracy73.91Unverified
#ModelMetricClaimedVerifiedStatus
1+U-DML*Inference Time (ms)675.56Unverified
2DenseAccuracy79Unverified
3AC/DCAccuracy78.2Unverified
4Beta-RankAccuracy74.01Unverified
5TAS-pruned ResNet-110Accuracy73.16Unverified
#ModelMetricClaimedVerifiedStatus
1TAS-pruned ResNet-110Accuracy94.33Unverified
2ShuffleNet – QuantisedInference Time (ms)23.15Unverified
3AlexNet – QuantisedInference Time (ms)5.23Unverified
4MobileNet – QuantisedInference Time (ms)4.74Unverified
#ModelMetricClaimedVerifiedStatus
1FFN-ShapleyPrunedAvg #Steps12.05Unverified