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 1301–1350 of 1356 papers

TitleStatusHype
Efficient Recurrent Neural Networks using Structured Matrices in FPGAs—0
Interpreting Deep Classifier by Visual Distillation of Dark Knowledge—0
Model compression via distillation and quantizationCode0
Paraphrasing Complex Network: Network Compression via Factor TransferCode0
AMC: AutoML for Model Compression and Acceleration on Mobile DevicesCode2
Model compression for faster structural separation of macromolecules captured by Cellular Electron Cryo-Tomography—0
DNN Model Compression Under Accuracy Constraints—0
Don't encrypt the data; just approximate the model \ Towards Secure Transaction and Fair Pricing of Training Data—0
Adaptive Quantization of Neural Networks—0
Learning Deep and Compact Models for Gesture RecognitionCode0
StrassenNets: Deep Learning with a Multiplication BudgetCode0
Learning Efficient Object Detection Models with Knowledge Distillation—0
Neural Regularized Domain Adaptation for Chinese Word Segmentation—0
MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Face ImagesCode0
Improved Bayesian Compression—0
Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy—0
Weightless: Lossy Weight Encoding For Deep Neural Network CompressionCode0
A Survey of Model Compression and Acceleration for Deep Neural Networks—0
Data-Free Knowledge Distillation for Deep Neural NetworksCode2
To prune, or not to prune: exploring the efficacy of pruning for model compressionCode1
Compressing Low Precision Deep Neural Networks Using Sparsity-Induced Regularization in Ternary Networks—0
N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning—0
Learning Intrinsic Sparse Structures within Long Short-Term MemoryCode0
A Deep Cascade Network for Unaligned Face Attribute Classification—0
Model Distillation with Knowledge Transfer from Face Classification to Alignment and Verification—0
DeepRebirth: Accelerating Deep Neural Network Execution on Mobile Devices—0
Model compression as constrained optimization, with application to neural nets. Part II: quantization—0
Model compression as constrained optimization, with application to neural nets. Part I: general framework—0
DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer—0
Tensor Contraction Layers for Parsimonious Deep Nets—0
Cross-lingual Distillation for Text ClassificationCode0
Acoustic Model Compression with MAP adaptation—0
Exploiting random projections and sparsity with random forests and gradient boosting methods -- Application to multi-label and multi-output learning, random forest model compression and leveraging input sparsity—0
A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation—0
Exploiting Domain Knowledge via Grouped Weight Sharing with Application to Text Categorization—0
Compression of Deep Neural Networks for Image Instance Retrieval—0
QuickNet: Maximizing Efficiency and Efficacy in Deep Architectures—0
Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices—0
Parameter Compression of Recurrent Neural Networks and Degradation of Short-term Memory—0
The Shallow End: Empowering Shallower Deep-Convolutional Networks through Auxiliary OutputsCode0
Deep Model Compression: Distilling Knowledge from Noisy Teachers—0
Ensemble-Compression: A New Method for Parallel Training of Deep Neural Networks—0
Ternary Weight NetworksCode1
Adapting Models to Signal Degradation using Distillation—0
On the Compression of Recurrent Neural Networks with an Application to LVCSR acoustic modeling for Embedded Speech Recognition—0
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizeCode1
Actor-Mimic: Deep Multitask and Transfer Reinforcement LearningCode0
Blending LSTMs into CNNs—0
Distilling Model KnowledgeCode0
DeepFont: Identify Your Font from An ImageCode0
Show:102550
← PrevPage 27 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