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 1151–1200 of 1356 papers

TitleStatusHype
Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System—0
Compacting, Picking and Growing for Unforgetting Continual LearningCode1
Structured Pruning of a BERT-based Question Answering Model—0
Model Fusion via Optimal TransportCode0
Structured Pruning of Large Language ModelsCode1
Differentiable Sparsification for Deep Neural Networks—0
Deep Neural Network Compression for Image Classification and Object DetectionCode0
How does topology influence gradient propagation and model performance of deep networks with DenseNet-type skip connections?Code0
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time SystemsCode1
Adversarial Robustness vs. Model Compression, or Both?Code0
REQ-YOLO: A Resource-Aware, Efficient Quantization Framework for Object Detection on FPGAs—0
Robust Membership Encoding: Inference Attacks and Copyright Protection for Deep Learning—0
Global Sparse Momentum SGD for Pruning Very Deep Neural NetworksCode1
Network Pruning for Low-Rank Binary Index—0
Decoupling Weight Regularization from Batch Size for Model Compression—0
GQ-Net: Training Quantization-Friendly Deep Networks—0
Atomic Compression Networks—0
Balancing Specialization, Generalization, and Compression for Detection and Tracking—0
Extremely Small BERT Models from Mixed-Vocabulary Training—0
Class-dependent Compression of Deep Neural NetworksCode0
Differentiable Mask for Pruning Convolutional and Recurrent Networks—0
PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices—0
LIT: Learned Intermediate Representation Training for Model CompressionCode0
Knowledge Distillation for End-to-End Person SearchCode0
Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation—0
On the Effectiveness of Low-Rank Matrix Factorization for LSTM Model Compression—0
Patient Knowledge Distillation for BERT Model CompressionCode0
Well-Read Students Learn Better: On the Importance of Pre-training Compact ModelsCode2
MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors—0
Einconv: Exploring Unexplored Tensor Network Decompositions for Convolutional Neural NetworksCode0
Tuning Algorithms and Generators for Efficient Edge Inference—0
Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT—0
Real-Time Correlation Tracking via Joint Model Compression and TransferCode0
Light Multi-segment Activation for Model CompressionCode0
Neural Epitome Search for Architecture-Agnostic Network Compression—0
Data-Independent Neural Pruning via Coresets—0
ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning—0
AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates—0
Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?—0
Weight Normalization based Quantization for Deep Neural Network Compression—0
COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level PruningCode0
Joint Regularization on Activations and Weights for Efficient Neural Network Pruning—0
Scalable Model Compression by Entropy Penalized Reparameterization—0
Membership Privacy for Machine Learning Models Through Knowledge Transfer—0
Does Learning Require Memorization? A Short Tale about a Long Tail—0
Network Implosion: Effective Model Compression for ResNets via Static Layer Pruning and Retraining—0
Deep Face Recognition Model Compression via Knowledge Transfer and Distillation—0
Compressing Convolutional Neural Networks via Factorized Convolutional FiltersCode0
Cross Domain Model Compression by Structurally Weight Sharing—0
Multi-Precision Quantized Neural Networks via Encoding Decomposition of -1 and +1—0
Show:102550
← PrevPage 24 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