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 1201–1250 of 1356 papers

TitleStatusHype
Bayesian Optimization with Clustering and Rollback for CNN Auto PruningCode0
GSB: Group Superposition Binarization for Vision Transformer with Limited Training SamplesCode0
Learning Accurate Performance Predictors for Ultrafast Automated Model CompressionCode0
Compressed Learning of Deep Neural Networks for OpenCL-Capable Embedded SystemsCode0
STD-NET: Search of Image Steganalytic Deep-learning Architecture via Hierarchical Tensor DecompositionCode0
Stealthy Backdoors as Compression ArtifactsCode0
Learning Compression from Limited Unlabeled DataCode0
Learning Deep and Compact Models for Gesture RecognitionCode0
On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep LearningCode0
Learning Efficient Detector with Semi-supervised Adaptive DistillationCode0
StrassenNets: Deep Learning with a Multiplication BudgetCode0
Application Specific Compression of Deep Learning ModelsCode0
Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural NetworksCode0
Annealing Knowledge DistillationCode0
On the Utility of Gradient Compression in Distributed Training SystemsCode0
Distilling Model KnowledgeCode0
Learning Intrinsic Sparse Structures within Long Short-Term MemoryCode0
Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer EncodersCode0
ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce ConnectionsCode0
TQCompressor: improving tensor decomposition methods in neural networks via permutationsCode0
Generalizing Teacher Networks for Effective Knowledge Distillation Across Student ArchitecturesCode0
Trainable pruned ternary quantization for medical signal classification modelsCode0
Comprehensive SNN Compression Using ADMM Optimization and Activity RegularizationCode0
A Computing Kernel for Network Binarization on PyTorchCode0
Robust and Large-Payload DNN Watermarking via Fixed, Distribution-Optimized, WeightsCode0
Towards Efficient Model Compression via Learned Global RankingCode0
GASL: Guided Attention for Sparsity Learning in Deep Neural NetworksCode0
Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher ModelCode0
Robust Model Compression Using Deep HypothesesCode0
From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model CompressionCode0
Robustness and Diversity Seeking Data-Free Knowledge DistillationCode0
Foundations of Large Language Model Compression -- Part 1: Weight QuantizationCode0
Light Multi-segment Activation for Model CompressionCode0
FLoCoRA: Federated learning compression with low-rank adaptationCode0
Distilling Focal Knowledge From Imperfect Expert for 3D Object DetectionCode0
Structured Pruning and Quantization for Learned Image CompressionCode0
LilNetX: Lightweight Networks with EXtreme Model Compression and Structured SparsificationCode0
FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model CompressionCode0
An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2Code0
OWLed: Outlier-weighed Layerwise Pruning for Efficient Autonomous Driving FrameworkCode0
Understanding the Effect of Model Compression on Social Bias in Large Language ModelsCode0
Few Shot Network Compression via Cross DistillationCode0
LIT: Learned Intermediate Representation Training for Model CompressionCode0
Lottery Aware Sparsity Hunting: Enabling Federated Learning on Resource-Limited EdgeCode0
Tiny Models are the Computational Saver for Large ModelsCode0
Finding Deviated Behaviors of the Compressed DNN Models for Image ClassificationsCode0
Rotation Invariant Quantization for Model CompressionCode0
Distilled Pruning: Using Synthetic Data to Win the LotteryCode0
Faithful Label-free Knowledge DistillationCode0
Paraphrasing Complex Network: Network Compression via Factor TransferCode0
Show:102550
← PrevPage 25 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