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 401425 of 534 papers

TitleStatusHype
Low-Rank Prune-And-Factorize for Language Model Compression0
MARS: Multi-macro Architecture SRAM CIM-Based Accelerator with Co-designed Compressed Neural Networks0
MaskConvNet: Training Efficient ConvNets from Scratch via Budget-constrained Filter Pruning0
Maximum Redundancy Pruning: A Principle-Driven Layerwise Sparsity Allocation for LLMs0
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks0
Improving Generalization in Meta-Learning via Meta-Gradient AugmentationCode0
Improving the Transferability of Adversarial Examples via Direction TuningCode0
Interpretations Steered Network Pruning via Amortized Inferred Saliency MapsCode0
Importance Estimation for Neural Network PruningCode0
Investigating the Effect of Network Pruning on Performance and InterpretabilityCode0
Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language ModelsCode0
Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude PruningCode0
3D Point Cloud Network Pruning: When Some Weights Do not MatterCode0
Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment ClassificationCode0
HALO: Learning to Prune Neural Networks with ShrinkageCode0
How I Learned to Stop Worrying and Love RetrainingCode0
Guiding Evolutionary AutoEncoder Training with Activation-Based Pruning OperatorsCode0
DASS: Differentiable Architecture Search for Sparse neural networksCode0
Few Sample Knowledge Distillation for Efficient Network CompressionCode0
Knowledge-Enhanced Semi-Supervised Federated Learning for Aggregating Heterogeneous Lightweight Clients in IoTCode0
ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint SearchCode0
A Fair Loss Function for Network PruningCode0
Global Magnitude Pruning With Minimum Threshold Is All We NeedCode0
L-CO-Net: Learned Condensation-Optimization Network for Clinical Parameter Estimation from Cardiac Cine MRICode0
LEAN: graph-based pruning for convolutional neural networks by extracting longest chainsCode0
Show:102550
← PrevPage 17 of 22Next →

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