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
Conditional Generative Data-free Knowledge Distillation—0
Conditional Teacher-Student Learning—0
Compact CNN Structure Learning by Knowledge Distillation—0
Communication-Efficient Federated Learning with Adaptive Compression under Dynamic Bandwidth—0
Communication-Efficient Distributed Online Learning with Kernels—0
Context-aware deep model compression for edge cloud computing—0
Continuous Approximations for Improving Quantization Aware Training of LLMs—0
CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders—0
Collaborative Teacher-Student Learning via Multiple Knowledge Transfer—0
Convolutional Neural Network Compression Based on Low-Rank Decomposition—0
Convolutional Neural Network Compression via Dynamic Parameter Rank Pruning—0
SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency—0
CORSD: Class-Oriented Relational Self Distillation—0
Cosine Similarity Knowledge Distillation for Individual Class Information Transfer—0
Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training—0
CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction—0
Integrating Fairness and Model Pruning Through Bi-level Optimization—0
Stability Based Filter Pruning for Accelerating Deep CNNs—0
Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization—0
CPTQuant -- A Novel Mixed Precision Post-Training Quantization Techniques for Large Language Models—0
Creating Lightweight Object Detectors with Model Compression for Deployment on Edge Devices—0
Croesus: Multi-Stage Processing and Transactions for Video-Analytics in Edge-Cloud Systems—0
Cross-Channel Intragroup Sparsity Neural Network—0
Cross Domain Model Compression by Structurally Weight Sharing—0
ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning—0
Effective Model Compression via Stage-wise Pruning—0
CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression—0
CSTAR: Towards Compact and STructured Deep Neural Networks with Adversarial Robustness—0
CURing Large Models: Compression via CUR Decomposition—0
D^2MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving—0
DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks—0
DARC: Differentiable ARchitecture Compression—0
DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer—0
Closed-Loop Neural Interfaces with Embedded Machine Learning—0
Data-Driven Compression of Convolutional Neural Networks—0
2-bit Conformer quantization for automatic speech recognition—0
Data-Free Adversarial Knowledge Distillation for Graph Neural Networks—0
Statistical Model Compression for Small-Footprint Natural Language Understanding—0
Data-Free Distillation of Language Model by Text-to-Text Transfer—0
Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications—0
Variational autoencoder-based neural network model compression—0
DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers—0
Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Images—0
Data-Free Knowledge Transfer: A Survey—0
Characterizing the Accuracy -- Efficiency Trade-off of Low-rank Decomposition in Language Models—0
Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning—0
Data-Free Quantization via Pseudo-label Filtering—0
Data-Independent Structured Pruning of Neural Networks via Coresets—0
Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices—0
Debiased Distillation by Transplanting the Last Layer—0
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