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 201–250 of 534 papers

TitleStatusHype
ExPAN(N)D: Exploring Posits for Efficient Artificial Neural Network Design in FPGA-based Systems—0
Improving Feature Attribution through Input-specific Network Pruning—0
Distortion-Aware Network Pruning and Feature Reuse for Real-time Video Segmentation—0
Exploring Neural Network Pruning with Screening Methods—0
Extract Local Inference Chains of Deep Neural Nets—0
CAP: Context-Aware Pruning for Semantic-Segmentation—0
An Efficient Row-Based Sparse Fine-Tuning—0
Fast as CHITA: Neural Network Pruning with Combinatorial Optimization—0
Cascade Weight Shedding in Deep Neural Networks: Benefits and Pitfalls for Network Pruning—0
Learning Pruned Structure and Weights Simultaneously from Scratch: an Attention based Approach—0
Less is More: The Influence of Pruning on the Explainability of CNNs—0
Accurate Neural Network Pruning Requires Rethinking Sparse Optimization—0
FedMef: Towards Memory-efficient Federated Dynamic Pruning—0
FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity—0
Analysing Neural Network Topologies: a Game Theoretic Approach—0
Distributed Pruning Towards Tiny Neural Networks in Federated Learning—0
Pruning-Aware Merging for Efficient Multitask Inference—0
Discriminative Adversarial Unlearning—0
AutoPruning for Deep Neural Network with Dynamic Channel Masking—0
Finding Deep Local Optima Using Network Pruning—0
Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning—0
DIPNet: Efficiency Distillation and Iterative Pruning for Image Super-Resolution—0
A Main/Subsidiary Network Framework for Simplifying Binary Neural Network—0
Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model—0
Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization—0
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 5 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