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 651–700 of 1356 papers

TitleStatusHype
Language model compression with weighted low-rank factorization—0
QUIDAM: A Framework for Quantization-Aware DNN Accelerator and Model Co-Exploration—0
QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design—0
Fundamental Limits of Communication Efficiency for Model Aggregation in Distributed Learning: A Rate-Distortion Approach—0
Representative Teacher Keys for Knowledge Distillation Model Compression Based on Attention Mechanism for Image Classification—0
An Automatic and Efficient BERT Pruning for Edge AI Systems—0
Knowledge Distillation for Oriented Object Detection on Aerial Images—0
Revisiting Self-Distillation—0
Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization—0
Atrial Fibrillation Detection Using Weight-Pruned, Log-Quantised Convolutional Neural Networks—0
STD-NET: Search of Image Steganalytic Deep-learning Architecture via Hierarchical Tensor DecompositionCode0
A Theoretical Understanding of Neural Network Compression from Sparse Linear Approximation—0
HideNseek: Federated Lottery Ticket via Server-side Pruning and Sign Supermask—0
DiSparse: Disentangled Sparsification for Multitask Model CompressionCode1
Differentially Private Model Compression—0
Canonical convolutional neural networksCode0
Resource Allocation for Compression-aided Federated Learning with High Distortion Rate—0
RLx2: Training a Sparse Deep Reinforcement Learning Model from ScratchCode1
Towards Efficient 3D Object Detection with Knowledge DistillationCode1
MiniDisc: Minimal Distillation Schedule for Language Model CompressionCode0
Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models—0
Do we need Label Regularization to Fine-tune Pre-trained Language Models?—0
PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D DetectionCode1
Aligning Logits Generatively for Principled Black-Box Knowledge DistillationCode0
InDistill: Information flow-preserving knowledge distillation for model compressionCode0
QAPPA: Quantization-Aware Power, Performance, and Area Modeling of DNN Accelerators—0
Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey—0
Perturbation of Deep Autoencoder Weights for Model Compression and Classification of Tabular Data—0
Chemical transformer compression for accelerating both training and inference of molecular modelingCode0
DNA data storage, sequencing data-carrying DNA—0
Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures—0
Data-Free Adversarial Knowledge Distillation for Graph Neural Networks—0
Automatic Block-wise Pruning with Auxiliary Gating Structures for Deep Convolutional Neural Networks—0
Online Model Compression for Federated Learning with Large Models—0
Can collaborative learning be private, robust and scalable?—0
Multi-Granularity Structural Knowledge Distillation for Language Model CompressionCode0
Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization—0
Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image RetrievalCode1
Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications—0
Neural Network Pruning by Cooperative Coevolution—0
Characterizing and Understanding the Behavior of Quantized Models for Reliable DeploymentCode0
Enabling All In-Edge Deep Learning: A Literature Review—0
LilNetX: Lightweight Networks with EXtreme Model Compression and Structured SparsificationCode0
Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse NetworkCode1
FedSynth: Gradient Compression via Synthetic Data in Federated Learning—0
Aligned Weight Regularizers for Pruning Pretrained Neural Networks—0
Structured Pruning Learns Compact and Accurate ModelsCode1
TextPruner: A Model Pruning Toolkit for Pre-Trained Language Models—0
Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks—0
CHEX: CHannel EXploration for CNN Model CompressionCode1
Show:102550
← PrevPage 14 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