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 476–500 of 1356 papers

TitleStatusHype
Accurate Neural Network Pruning Requires Rethinking Sparse Optimization—0
MIMONet: Multi-Input Multi-Output On-Device Deep Learning—0
Model Compression Methods for YOLOv5: A Review—0
Impact of Disentanglement on Pruning Neural Networks—0
Knowledge Distillation for Object Detection: from generic to remote sensing datasets—0
CA-LoRA: Adapting Existing LoRA for Compressed LLMs to Enable Efficient Multi-Tasking on Personal DevicesCode0
Distilled Pruning: Using Synthetic Data to Win the LotteryCode0
Distilling Universal and Joint Knowledge for Cross-Domain Model Compression on Time Series DataCode0
TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition—0
Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning—0
Quantization Variation: A New Perspective on Training Transformers with Low-Bit PrecisionCode1
An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs—0
Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer InferenceCode1
Feature Adversarial Distillation for Point Cloud Classification—0
Low-Rank Prune-And-Factorize for Language Model Compression—0
Partitioning-Guided K-Means: Extreme Empty Cluster Resolution for Extreme Model Compression—0
Data-Free Backbone Fine-Tuning for Pruned Neural NetworksCode0
LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation—0
DynaQuant: Compressing Deep Learning Training Checkpoints via Dynamic Quantization—0
CrossKD: Cross-Head Knowledge Distillation for Object DetectionCode1
HiNeRV: Video Compression with Hierarchical Encoding-based Neural RepresentationCode1
Neural Network Compression using Binarization and Few Full-Precision Weights—0
Efficient and Robust Quantization-aware Training via Adaptive Coreset SelectionCode1
Deep Model Compression Also Helps Models Capture AmbiguityCode0
A Brief Review of Hypernetworks in Deep LearningCode0
Show:102550
← PrevPage 20 of 55Next →
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