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 451–500 of 534 papers

TitleStatusHype
Quantum-Inspired Hamiltonian Monte Carlo for Bayesian SamplingCode0
AutoPrune: Automatic Network Pruning by Regularizing Auxiliary ParametersCode0
One-Shot Pruning of Recurrent Neural Networks by Jacobian Spectrum Evaluation—0
Improving Feature Attribution through Input-specific Network Pruning—0
Neural Network Pruning with Residual-Connections and Limited-DataCode0
DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks—0
What Do Compressed Deep Neural Networks Forget?Code0
Iteratively Training Look-Up Tables for Network Quantization—0
Cross-Channel Intragroup Sparsity Neural Network—0
Self-Adaptive Network Pruning—0
Privacy Preserving Stochastic Channel-Based Federated Learning with Neural Network Pruning—0
ConfusionFlow: A model-agnostic visualization for temporal analysis of classifier confusion—0
Pruning from ScratchCode0
Network Pruning for Low-Rank Binary Index—0
On the Decision Boundaries of Deep Neural Networks: A Tropical Geometry Perspective—0
Finding Deep Local Optima Using Network Pruning—0
Selective Brain Damage: Measuring the Disparate Impact of Model Pruning—0
Meta-Learning with Network Pruning for Overfitting Reduction—0
Class-dependent Compression of Deep Neural NetworksCode0
Defeating Misclassification Attacks Against Transfer Learning—0
Architecture-aware Network Pruning for Vision Quality Applications—0
Data-Independent Neural Pruning via Coresets—0
A Targeted Acceleration and Compression Framework for Low bit Neural Networks—0
Importance Estimation for Neural Network PruningCode0
Joint Regularization on Activations and Weights for Efficient Neural Network Pruning—0
Structured Pruning of Recurrent Neural Networks through Neuron Selection—0
A Signal Propagation Perspective for Pruning Neural Networks at InitializationCode0
Towards Compact and Robust Deep Neural Networks—0
The Generalization-Stability Tradeoff In Neural Network Pruning—0
Variational Convolutional Neural Network Pruning—0
Learning Sparse Networks Using Targeted DropoutCode0
Network Pruning via Transformable Architecture SearchCode0
Pruning-Aware Merging for Efficient Multitask Inference—0
EigenDamage: Structured Pruning in the Kronecker-Factored EigenbasisCode0
Network Pruning for Low-Rank Binary Indexing—0
Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural NetworksCode0
Analysing Neural Network Topologies: a Game Theoretic Approach—0
C2S2: Cost-aware Channel Sparse Selection for Progressive Network Pruning—0
Progressive Stochastic Binarization of Deep NetworksCode0
Adversarial Robustness vs Model Compression, or Both?Code0
FastDepth: Fast Monocular Depth Estimation on Embedded SystemsCode0
Single-shot Channel Pruning Based on Alternating Direction Method of Multipliers—0
Same, Same But Different - Recovering Neural Network Quantization Error Through Weight FactorizationCode0
DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy CompressionCode0
GASL: Guided Attention for Sparsity Learning in Deep Neural NetworksCode0
A Main/Subsidiary Network Framework for Simplifying Binary Neural Network—0
Few Sample Knowledge Distillation for Efficient Network CompressionCode0
Channel-wise pruning of neural networks with tapering resource constraint—0
Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource UtilizationCode0
Efficient Structured Pruning and Architecture Searching for Group ConvolutionCode0
Show:102550
← PrevPage 10 of 11Next →
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