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 276–300 of 534 papers

TitleStatusHype
Pruning for Feature-Preserving Circuits in CNNsCode0
Towards Communication-Learning Trade-off for Federated Learning at the Network Edge—0
Pruning has a disparate impact on model accuracy—0
Compression-aware Training of Neural Networks using Frank-WolfeCode0
Hyperparameter Optimization with Neural Network Pruning—0
Automatic Block-wise Pruning with Auxiliary Gating Structures for Deep Convolutional Neural Networks—0
Neural Network Pruning by Cooperative Coevolution—0
Supervised Robustness-preserving Data-free Neural Network PruningCode0
AutoAdversary: A Pixel Pruning Method for Sparse Adversarial Attack—0
Improve Convolutional Neural Network Pruning by Maximizing Filter Variety—0
A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation—0
A Study of Designing Compact Audio-Visual Wake Word Spotting System Based on Iterative Fine-Tuning in Neural Network Pruning—0
PRUNIX: Non-Ideality Aware Convolutional Neural Network Pruning for Memristive Accelerators—0
Win the Lottery Ticket via Fourier Analysis: Frequencies Guided Network Pruning—0
Pruning-aware Sparse Regularization for Network PruningCode0
Why Does DARTS Miss the Target, and How Do We Aim to Fix It?—0
Automatic Sparse Connectivity Learning for Neural Networks—0
Towards Lightweight Neural Animation : Exploration of Neural Network Pruning in Mixture of Experts-based Animation Models—0
Neural Network Optimization for Reinforcement Learning Tasks Using Sparse Computations—0
Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning—0
Pruning deep neural networks generates a sparse, bio-inspired nonlinear controller for insect flightCode0
Distilling the Knowledge of Romanian BERTs Using Multiple TeachersCode0
Network Compression via Central FilterCode0
Enhanced Exploration in Neural Feature Selection for Deep Click-Through Rate Prediction Models via Ensemble of Gating Layers—0
Putting 3D Spatially Sparse Networks on a Diet—0
Show:102550
← PrevPage 12 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