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 1001–1050 of 1356 papers

TitleStatusHype
Task-Agnostic and Adaptive-Size BERT Compression—0
A Half-Space Stochastic Projected Gradient Method for Group Sparsity Regularization—0
BinaryBERT: Pushing the Limit of BERT Quantization—0
Towards Zero-Shot Knowledge Distillation for Natural Language Processing—0
Enabling Retrain-free Deep Neural Network Pruning using Surrogate Lagrangian Relaxation—0
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks—0
Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces—0
Wasserstein Contrastive Representation Distillation—0
Reinforced Multi-Teacher Selection for Knowledge Distillation—0
Large-Scale Generative Data-Free Distillation—0
Inferring ECG from PPG for Continuous Cardiac Monitoring Using Lightweight Neural Network—0
Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework—0
Model Compression Using Optimal Transport—0
Multi-head Knowledge Distillation for Model Compression—0
Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains—0
Compressing Pre-trained Language Models by Matrix Decomposition—0
Self-Supervised Generative Adversarial Compression—0
NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration—0
Edge Deep Learning for Neural Implants—0
Reverse-engineering recurrent neural network solutions to a hierarchical inference task for mice—0
Extreme Model Compression for On-device Natural Language Understanding—0
A Selective Survey on Versatile Knowledge Distillation Paradigm for Neural Network Models—0
Context-aware deep model compression for edge cloud computing—0
Bringing AI To Edge: From Deep Learning's Perspective—0
Auto Graph Encoder-Decoder for Neural Network Pruning—0
torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation—0
Empirical Evaluation of Deep Learning Model Compression Techniques on the WaveNet VocoderCode0
MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing—0
Online Ensemble Model Compression using Knowledge DistillationCode0
Automated Model Compression by Jointly Applied Pruning and Quantization—0
Effective Model Compression via Stage-wise Pruning—0
Neural Network Compression Via Sparse Optimization—0
Knowledge Distillation for Singing Voice DetectionCode0
Robustness and Diversity Seeking Data-Free Knowledge DistillationCode0
Know What You Don't Need: Single-Shot Meta-Pruning for Attention Heads—0
Self-Supervised Learning from Contrastive Mixtures for Personalized Speech EnhancementCode0
A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNsCode0
Watermarking Graph Neural Networks by Random Graphs—0
Exploring the Boundaries of Low-Resource BERT Distillation—0
Activation Map Adaptation for Effective Knowledge Distillation—0
MARS: Multi-macro Architecture SRAM CIM-Based Accelerator with Co-designed Compressed Neural Networks—0
AutoBSS: An Efficient Algorithm for Block Stacking Style Search—0
Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher—0
Noisy Neural Network Compression for Analog Storage Devices—0
Closed-Loop Neural Interfaces with Embedded Machine Learning—0
Weight Squeezing: Reparameterization for Knowledge Transfer and Model Compression—0
A Model Compression Method with Matrix Product Operators for Speech Enhancement—0
Compressing Deep Convolutional Neural Networks by Stacking Low-dimensional Binary Convolution Filters—0
GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep Learning—0
Pea-KD: Parameter-efficient and Accurate Knowledge Distillation on BERT—0
Show:102550
← PrevPage 21 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