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 351400 of 534 papers

TitleStatusHype
MARS: Multi-macro Architecture SRAM CIM-Based Accelerator with Co-designed Compressed Neural Networks0
ExPAN(N)D: Exploring Posits for Efficient Artificial Neural Network Design in FPGA-based Systems0
AutoPruning for Deep Neural Network with Dynamic Channel Masking0
SCOP: Scientific Control for Reliable Neural Network PruningCode1
Softer Pruning, Incremental Regularization0
Layer-adaptive sparsity for the Magnitude-based PruningCode1
Coarse and fine-grained automatic cropping deep convolutional neural network0
Advanced Dropout: A Model-free Methodology for Bayesian Dropout OptimizationCode1
Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework0
Comprehensive Online Network Pruning via Learnable Scaling Factors0
A Survey on Deep Neural Network Compression: Challenges, Overview, and Solutions0
A Gradient Flow Framework For Analyzing Network PruningCode1
Sanity-Checking Pruning Methods: Random Tickets can Win the JackpotCode1
On the Landscape of One-hidden-layer Sparse Networks and Beyond0
On the use of local structural properties for improving the efficiency of hierarchical community detection methods0
Achieving Adversarial Robustness via Sparsity0
Enabling Image Recognition on Constrained Devices Using Neural Network Pruning and a CycleGAN0
Prune Responsibly0
OrthoReg: Robust Network Pruning Using Orthonormality RegularizationCode0
Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise SparsityCode1
SparseRT: Accelerating Unstructured Sparsity on GPUs for Deep Learning Inference0
HALO: Learning to Prune Neural Networks with ShrinkageCode0
RARTS: An Efficient First-Order Relaxed Architecture Search Method0
Hierarchical Action Classification with Network Pruning0
Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning0
Meta-Learning with Network Pruning0
EagleEye: Fast Sub-net Evaluation for Efficient Neural Network PruningCode1
Weight-dependent Gates for Network Pruning0
Statistical Mechanical Analysis of Neural Network PruningCode0
ESPN: Extremely Sparse Pruned NetworksCode0
Rapid Structural Pruning of Neural Networks with Set-based Task-Adaptive Meta-Pruning0
Paying more attention to snapshots of Iterative Pruning: Improving Model Compression via Ensemble DistillationCode1
Cogradient Descent for Bilinear Optimization0
dagger: A Python Framework for Reproducible Machine Learning Experiment Orchestration0
A Framework for Neural Network Pruning Using Gibbs DistributionsCode0
ADMP: An Adversarial Double Masks Based Pruning Framework For Unsupervised Cross-Domain Compression0
Weight Pruning via Adaptive Sparsity LossCode1
Shapley Value as Principled Metric for Structured Network PruningCode1
A Feature-map Discriminant Perspective for Pruning Deep Neural Networks0
Bayesian Neural Networks at Scale: A Performance Analysis and Pruning Study0
MicroNet for Efficient Language ModelingCode1
A flexible, extensible software framework for model compression based on the LC algorithm0
Movement Pruning: Adaptive Sparsity by Fine-TuningCode1
Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked LayersCode1
Pruning coupled with learning, ensembles of minimal neural networks, and future of XAI0
Compact Neural Representation Using Attentive Network Pruning0
GPU Acceleration of Sparse Neural Networks0
Streamlining Tensor and Network Pruning in PyTorch0
L-CO-Net: Learned Condensation-Optimization Network for Clinical Parameter Estimation from Cardiac Cine MRICode0
Network Adjustment: Channel Search Guided by FLOPs Utilization RatioCode1
Show:102550
← PrevPage 8 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