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 1101–1150 of 1356 papers

TitleStatusHype
Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs—0
Variational Bayesian QuantizationCode1
PCNN: Pattern-based Fine-Grained Regular Pruning towards Optimizing CNN Accelerators—0
Understanding and Improving Knowledge Distillation—0
BERT-of-Theseus: Compressing BERT by Progressive Module ReplacingCode1
Lightweight Convolutional Representations for On-Device Natural Language Processing—0
Search for Better Students to Learn Distilled Knowledge—0
MT-BioNER: Multi-task Learning for Biomedical Named Entity Recognition using Deep Bidirectional Transformers—0
Small, Accurate, and Fast Vehicle Re-ID on the Edge: the SAFR Approach—0
SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency—0
A "Network Pruning Network" Approach to Deep Model Compression—0
Discrimination-aware Network Pruning for Deep Model CompressionCode1
FedBoost: A Communication-Efficient Algorithm for Federated Learning—0
ZeroQ: A Novel Zero Shot Quantization FrameworkCode1
PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning—0
Differentiable Architecture Compression—0
DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier—0
Domain Adaptation Regularization for Spectral Pruning—0
Data-Free Adversarial DistillationCode0
Pruning by Explaining: A Novel Criterion for Deep Neural Network PruningCode0
Towards Building a Real Time Mobile Device Bird Counting System Through Synthetic Data Training and Model Compression—0
An Improving Framework of regularization for Network Compression—0
Explaining Sequence-Level Knowledge Distillation as Data-Augmentation for Neural Machine Translation—0
Deep Model Compression Via Two-Stage Deep Reinforcement Learning—0
The Knowledge Within: Methods for Data-Free Model Compression—0
TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLPCode0
Exploring Unexplored Tensor Network Decompositions for Convolutional Neural NetworksCode0
Pruning at a Glance: Global Neural Pruning for Model Compression—0
Data-Driven Compression of Convolutional Neural Networks—0
Communication-Efficient Distributed Online Learning with Kernels—0
Structured Multi-Hashing for Model Compression—0
A SOT-MRAM-based Processing-In-Memory Engine for Highly Compressed DNN Implementation—0
Graph Pruning for Model Compression—0
Few Shot Network Compression via Cross DistillationCode0
On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep LearningCode0
DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks—0
Distributed Low Precision Training Without Mixed Precision—0
ASCAI: Adaptive Sampling for acquiring Compact AI—0
Data Efficient Stagewise Knowledge DistillationCode0
Learning from a Teacher using Unlabeled DataCode1
What Do Compressed Deep Neural Networks Forget?Code0
A Computing Kernel for Network Binarization on PyTorchCode0
SubCharacter Chinese-English Neural Machine Translation with Wubi encoding—0
A Programmable Approach to Neural Network CompressionCode0
Localization-aware Channel Pruning for Object Detection—0
Comprehensive SNN Compression Using ADMM Optimization and Activity RegularizationCode0
Locality-Sensitive Hashing for f-Divergences: Mutual Information Loss and Beyond—0
Cross-Channel Intragroup Sparsity Neural Network—0
LPRNet: Lightweight Deep Network by Low-rank Pointwise Residual Convolution—0
Contrastive Representation DistillationCode1
Show:102550
← PrevPage 23 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