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 151200 of 534 papers

TitleStatusHype
Network Pruning via Transformable Architecture SearchCode0
Efficient Incorporation of Multiple Latency Targets in the Once-For-All NetworkCode0
Network Compression via Central FilterCode0
Network Pruning via Feature Shift MinimizationCode0
Neural Architecture Codesign for Fast Physics ApplicationsCode0
3D Point Cloud Network Pruning: When Some Weights Do not MatterCode0
B-FPGM: Lightweight Face Detection via Bayesian-Optimized Soft FPGM PruningCode0
Model compression as constrained optimization, with application to neural nets. Part V: combining compressionsCode0
An empirical study of a pruning mechanismCode0
Beta-Rank: A Robust Convolutional Filter Pruning Method For Imbalanced Medical Image AnalysisCode0
Structured Sparsification with Joint Optimization of Group Convolution and Channel ShuffleCode0
Neural network is heterogeneous: Phase matters moreCode0
Dreaming to Distill: Data-free Knowledge Transfer via DeepInversionCode0
Magnitude and Similarity based Variable Rate Filter Pruning for Efficient Convolution Neural NetworksCode0
Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two BenchmarksCode0
Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the EdgeCode0
LLM-Rank: A Graph Theoretical Approach to Pruning Large Language ModelsCode0
How I Learned to Stop Worrying and Love RetrainingCode0
Lost in Pruning: The Effects of Pruning Neural Networks beyond Test AccuracyCode0
Max-Affine Spline Insights Into Deep Network PruningCode0
Distilling the Knowledge of Romanian BERTs Using Multiple TeachersCode0
Distilled Pruning: Using Synthetic Data to Win the LotteryCode0
Efficient Structured Pruning and Architecture Searching for Group ConvolutionCode0
Learning Sparse Networks Using Targeted DropoutCode0
Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language ModelsCode0
AutoPrune: Automatic Network Pruning by Regularizing Auxiliary ParametersCode0
L-CO-Net: Learned Condensation-Optimization Network for Clinical Parameter Estimation from Cardiac Cine MRICode0
DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and L_0 RegularizationCode0
Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI FeedbackCode0
EDAC: Efficient Deployment of Audio Classification Models For COVID-19 DetectionCode0
Adaptive Search-and-Training for Robust and Efficient Network PruningCode0
LEAN: graph-based pruning for convolutional neural networks by extracting longest chainsCode0
Neural Network Panning: Screening the Optimal Sparse Network Before TrainingCode0
Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude PruningCode0
Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment ClassificationCode0
Investigating the Effect of Network Pruning on Performance and InterpretabilityCode0
Device-Wise Federated Network PruningCode0
Dep-L_0: Improving L_0-based Network Sparsification via Dependency ModelingCode0
Interpretations Steered Network Pruning via Amortized Inferred Saliency MapsCode0
Boosting Large Language Models with Mask Fine-TuningCode0
DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy CompressionCode0
Importance Estimation for Neural Network PruningCode0
“Learning-Compression” Algorithms for Neural Net PruningCode0
Improving Generalization in Meta-Learning via Meta-Gradient AugmentationCode0
Guiding Evolutionary AutoEncoder Training with Activation-Based Pruning OperatorsCode0
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman CodingCode0
HALO: Learning to Prune Neural Networks with ShrinkageCode0
Class-dependent Compression of Deep Neural NetworksCode0
Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language ModelsCode0
Improving the Transferability of Adversarial Examples via Direction TuningCode0
Show:102550
← PrevPage 4 of 11Next →

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