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 226–250 of 534 papers

TitleStatusHype
Automatic Sparse Connectivity Learning for Neural Networks—0
Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices—0
Coarse and fine-grained automatic cropping deep convolutional neural network—0
GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization—0
Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regions—0
Differential Privacy Meets Neural Network Pruning—0
Adaptive Neural Connections for Sparsity Learning—0
Learning Compact Neural Networks with Regularization—0
GPU Acceleration of Sparse Neural Networks—0
LearningGroup: A Real-Time Sparse Training on FPGA via Learnable Weight Grouping for Multi-Agent Reinforcement Learning—0
Graph Attention Network based Pruning for Reconstructing 3D Liver Vessel Morphology from Contrasted CT Images—0
Explicit Group Sparse Projection with Applications to Deep Learning and NMF—0
Differentiable Network Pruning for Microcontrollers—0
Compact Neural Representation Using Attentive Network Pruning—0
Hierarchical Action Classification with Network Pruning—0
Differentiable Channel Sparsity Search via Weight Sharing within Filters—0
Hierarchical Human Action Classification with Network Pruning—0
Automatic Pruning via Structured Lasso with Class-wise Information—0
Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis—0
A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification—0
Automatic Block-wise Pruning with Auxiliary Gating Structures for Deep Convolutional Neural Networks—0
Hyperflows: Pruning Reveals the Importance of Weights—0
Hyperparameter Optimization with Neural Network Pruning—0
Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum—0
Heterogeneous Federated Learning using Dynamic Model Pruning and Adaptive Gradient—0
Show:102550
← PrevPage 10 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