SOTAVerified

Model Compression

Model Compression is an actively pursued area of research over the last few years with the goal of deploying state-of-the-art deep networks in low-power and resource limited devices without significant drop in accuracy. Parameter pruning, low-rank factorization and weight quantization are some of the proposed methods to compress the size of deep networks.

Source: KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1251–1300 of 1356 papers

TitleStatusHype
GASL: Guided Attention for Sparsity Learning in Deep Neural NetworksCode0
Exploring the 3D architectures of deep material network in data-driven multiscale mechanics—0
Natively Interpretable Machine Learning and Artificial Intelligence: Preliminary Results and Future Directions—0
Learning Efficient Detector with Semi-supervised Adaptive DistillationCode0
A Low Effort Approach to Structured CNN Design Using PCA—0
Exploiting Kernel Sparsity and Entropy for Interpretable CNN CompressionCode0
Stochastic Model Pruning via Weight Dropping Away and Back—0
Teacher-Student Compression with Generative Adversarial NetworksCode0
Leveraging Filter Correlations for Deep Model Compression—0
A Survey of Mobile Computing for the Visually Impaired—0
Joint Neural Architecture Search and Quantization—0
Graph-Adaptive Pruning for Efficient Inference of Convolutional Neural Networks—0
Stability Based Filter Pruning for Accelerating Deep CNNs—0
Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method—0
Private Model Compression via Knowledge Distillation—0
Sequence-Level Knowledge Distillation for Model Compression of Attention-based Sequence-to-Sequence Speech Recognition—0
FLOPs as a Direct Optimization Objective for Learning Sparse Neural Networks—0
A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM—0
JavaScript Convolutional Neural Networks for Keyword Spotting in the Browser: An Experimental AnalysisCode0
DeepTwist: Learning Model Compression via Occasional Weight Distortion—0
A Miniaturized Semantic Segmentation Method for Remote Sensing ImageCode0
Distilling with Performance Enhanced Students—0
To Compress, or Not to Compress: Characterizing Deep Learning Model Compression for Embedded Inference—0
Pruning at a Glance: A Structured Class-Blind Pruning Technique for Model Compression—0
Compression of Deep Neural Networks by combining pruning and low rank decomposition—0
Block-wise Intermediate Representation Training for Model Compression—0
Recurrent Convolutions: A Model Compression Point of View—0
PocketFlow: An Automated Framework for Compressing and Accelerating Deep Neural NetworksCode0
Progressive Weight Pruning of Deep Neural Networks using ADMM—0
Rate Distortion For Model Compression: From Theory To Practice—0
Efficient Computation of Quantized Neural Networks by −1, +1 Encoding Decomposition—0
LIT: Block-wise Intermediate Representation Training for Model Compression—0
Frustratingly Easy Model Ensemble for Abstractive Summarization—0
MLPrune: Multi-Layer Pruning for Automated Neural Network Compression—0
Learning Compression from Limited Unlabeled DataCode0
Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error—0
On-Device Neural Language Model Based Word PredictionCode0
Compressible Spectral Mixture Kernels with Sparse Dependency Structures for Gaussian Processes—0
SlimNets: An Exploration of Deep Model Compression and AccelerationCode0
StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNsCode0
A Unified Approximation Framework for Compressing and Accelerating Deep Neural Networks—0
Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy—0
Statistical Model Compression for Small-Footprint Natural Language Understanding—0
SGAD: Soft-Guided Adaptively-Dropped Neural Network—0
GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking—0
SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Manners—0
Dynamically Hierarchy Revolution: DirNet for Compressing Recurrent Neural Network on Mobile Devices—0
“Learning-Compression” Algorithms for Neural Net Pruning—0
Retraining-Based Iterative Weight Quantization for Deep Neural Networks—0
Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compression—0
Show:102550
← PrevPage 26 of 28Next →
All datasetsImageNetQNLI

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ADLIK-MO-ResNet50+W4A4Top-177.88—Unverified
2ADLIK-MO-ResNet50+W3A4Top-177.34—Unverified
3ResNet-18 + 4bit-1dim model compression using DKMTop-170.52—Unverified
4MobileNet-v1 + 4bit-1dim model compression using DKMTop-169.63—Unverified
5ResNet-18 + 2bit-1dim model compression using DKMTop-168.63—Unverified
6MobileNet-v1 + 2bit-1dim model compression using DKMTop-167.62—Unverified
7ResNet-18 + 4bit-4dim model compression using DKMTop-166.1—Unverified
8ResNet-18 + 2bit-2dim model compression using DKMTop-164.7—Unverified
9MobileNet-v1 + 4bit-4dim model compression using DKMTop-161.4—Unverified
10ResNet-18 + 1bit-1dim model compression using DKMTop-159.7—Unverified
#ModelMetricClaimedVerifiedStatus
1MobileBERT + 2bit-1dim model compression using DKMAccuracy82.13—Unverified
2MobileBERT + 1bit-1dim model compression using DKMAccuracy63.17—Unverified