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 301–350 of 534 papers

TitleStatusHype
Troubleshooting Blind Image Quality Models in the Wild—0
Dynamical Isometry: The Missing Ingredient for Neural Network Pruning—0
Network Pruning That Matters: A Case Study on Retraining VariantsCode1
Effective Sparsification of Neural Networks with Global Sparsity ConstraintCode1
Post-training deep neural network pruning via layer-wise calibration—0
Lottery Jackpots Exist in Pre-trained ModelsCode1
Rethinking Network Pruning -- under the Pre-train and Fine-tune ParadigmCode0
Convolutional Neural Network Pruning with Structural Redundancy Reduction—0
EfficientTDNN: Efficient Architecture Search for Speaker RecognitionCode1
Cascade Weight Shedding in Deep Neural Networks: Benefits and Pitfalls for Network Pruning—0
Recent Advances on Neural Network Pruning at InitializationCode1
Manifold Regularized Dynamic Network PruningCode1
Understanding Diversity Based Neural Network Pruning in Teacher Student Setup—0
Lost in Pruning: The Effects of Pruning Neural Networks beyond Test AccuracyCode0
Network Pruning via Resource ReallocationCode1
Knowledge Distillation Circumvents Nonlinearity for Optical Convolutional Neural Networks—0
Feature Selection for Multivariate Time Series via Network PruningCode0
Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement LearningCode1
Network Pruning using Adaptive Exemplar FiltersCode1
Multi-Task Network Pruning and Embedded Optimization for Real-time Deployment in ADAS—0
Network Automatic Pruning: Start NAP and Take a Nap—0
Single-path Bit Sharing for Automatic Loss-aware Model Compression—0
Max-Affine Spline Insights Into Deep Network PruningCode0
CAP-Context-Aware-Pruning-for-Semantic-Segmentation—0
CAP: Context-Aware Pruning for Semantic-Segmentation—0
On the Landscape of Sparse Linear Networks—0
Extract Local Inference Chains of Deep Neural Nets—0
Waste not, Want not: All-Alive Pruning for Extremely Sparse Networks—0
On the Decision Boundaries of Neural Networks. A Tropical Geometry Perspective—0
An empirical study of a pruning mechanismCode0
Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning—0
When Are Neural Pruning Approximation Bounds Useful?—0
Rapid Neural Pruning for Novel Datasets with Set-based Task-Adaptive Meta-Pruning—0
Spectral Analysis for Semantic Segmentation with Applications on Feature Truncation and Weak Annotation—0
Enabling Retrain-free Deep Neural Network Pruning using Surrogate Lagrangian Relaxation—0
Neural Pruning via Growing RegularizationCode1
Efficient Incorporation of Multiple Latency Targets in the Once-For-All NetworkCode0
Hierarchical Human Action Classification with Network Pruning—0
DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and L_0 RegularizationCode0
NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration—0
Robust error bounds for quantised and pruned neural networksCode0
EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference—0
Auto Graph Encoder-Decoder for Neural Network Pruning—0
Rethinking Weight Decay For Efficient Neural Network PruningCode0
LEAN: graph-based pruning for convolutional neural networks by extracting longest chainsCode0
Automated Model Compression by Jointly Applied Pruning and Quantization—0
Channel Planting for Deep Neural Networks using Knowledge Distillation—0
Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices—0
Differentiable Channel Sparsity Search via Weight Sharing within Filters—0
Neuron Merging: Compensating for Pruned NeuronsCode1
Show:102550
← PrevPage 7 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