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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 301–325 of 534 papers

TitleStatusHype
Bi-LSTM based Multi-Agent DRL with Computation-aware Pruning for Agent Twins Migration in Vehicular Embodied AI Networks—0
Surrogate Lagrangian Relaxation: A Path To Retrain-free Deep Neural Network Pruning—0
Maximum Redundancy Pruning: A Principle-Driven Layerwise Sparsity Allocation for LLMs—0
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks—0
Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures—0
Mini-batch Coresets for Memory-efficient Training of Large Language Models—0
Meta-Learning with Network Pruning—0
Meta-Learning with Network Pruning for Overfitting Reduction—0
Bayesian Neural Networks at Scale: A Performance Analysis and Pruning Study—0
The Generalization-Stability Tradeoff In Neural Network Pruning—0
Model compression as constrained optimization, with application to neural nets. Part V: combining compressions—0
Model Compression Methods for YOLOv5: A Review—0
Model Pruning Enables Localized and Efficient Federated Learning for Yield Forecasting and Data Sharing—0
Basis Scaling and Double Pruning for Efficient Inference in Network-Based Transfer Learning—0
Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systems—0
Multistage Pruning of CNN Based ECG Classifiers for Edge Devices—0
Multi-Task Network Pruning and Embedded Optimization for Real-time Deployment in ADAS—0
Mutual Information Preserving Neural Network Pruning—0
N2NSkip: Learning Highly Sparse Networks using Neuron-to-Neuron Skip Connections—0
NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm—0
Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning—0
Network Automatic Pruning: Start NAP and Take a Nap—0
The Incredible Shrinking Neural Network: New Perspectives on Learning Representations Through The Lens of Pruning—0
Network Pruning by Greedy Subnetwork Selection—0
Network Pruning for Low-Rank Binary Index—0
Show:102550
← PrevPage 13 of 22Next →
All datasetsImageNetImageNet - ResNet 50 - 90% sparsityCIFAR-100CIFAR-10MNIST

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50-2.3 GFLOPsAccuracy78.79—Unverified
2ResNet50-1.5 GFLOPsAccuracy78.07—Unverified
3ResNet50 2.5 GFLOPSAccuracy78—Unverified
4RegX-1.6GAccuracy77.97—Unverified
5ResNet50 2.0 GFLOPSAccuracy77.7—Unverified
6ResNet50-3G FLOPsAccuracy77.1—Unverified
7ResNet50-2G FLOPsAccuracy76.4—Unverified
8ResNet50-1G FLOPsAccuracy76.38—Unverified
9TAS-pruned ResNet-50Accuracy76.2—Unverified
10ResNet50Accuracy75.59—Unverified
#ModelMetricClaimedVerifiedStatus
1FeatherTop-1 Accuracy76.93—Unverified
2SpartanTop-1 Accuracy76.17—Unverified
3ST-3Top-1 Accuracy76.03—Unverified
4AC/DCTop-1 Accuracy75.64—Unverified
5CSTop-1 Accuracy75.5—Unverified
6ProbMaskTop-1 Accuracy74.68—Unverified
7STRTop-1 Accuracy74.31—Unverified
8DNWTop-1 Accuracy74—Unverified
9GMPTop-1 Accuracy73.91—Unverified
#ModelMetricClaimedVerifiedStatus
1+U-DML*Inference Time (ms)675.56—Unverified
2DenseAccuracy79—Unverified
3AC/DCAccuracy78.2—Unverified
4Beta-RankAccuracy74.01—Unverified
5TAS-pruned ResNet-110Accuracy73.16—Unverified
#ModelMetricClaimedVerifiedStatus
1TAS-pruned ResNet-110Accuracy94.33—Unverified
2ShuffleNet – QuantisedInference Time (ms)23.15—Unverified
3AlexNet – QuantisedInference Time (ms)5.23—Unverified
4MobileNet – QuantisedInference Time (ms)4.74—Unverified
#ModelMetricClaimedVerifiedStatus
1FFN-ShapleyPrunedAvg #Steps12.05—Unverified