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 51–75 of 1356 papers

TitleStatusHype
Distilling Object Detectors with Feature RichnessCode1
Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic HashingCode1
DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and TransformersCode1
Dual Relation Knowledge Distillation for Object DetectionCode1
CHEX: CHannel EXploration for CNN Model CompressionCode1
Model LEGO: Creating Models Like Disassembling and Assembling Building BlocksCode1
Class Attention Transfer Based Knowledge DistillationCode1
Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated LearningCode1
3DG-STFM: 3D Geometric Guided Student-Teacher Feature MatchingCode1
AD-KD: Attribution-Driven Knowledge Distillation for Language Model CompressionCode1
ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of MultipliersCode1
COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision ModelsCode1
DE-RRD: A Knowledge Distillation Framework for Recommender SystemCode1
A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution RobustnessCode1
Backdoor Attacks on Federated Learning with Lottery Ticket HypothesisCode1
Densely Guided Knowledge Distillation using Multiple Teacher AssistantsCode1
Differentiable Model Compression via Pseudo Quantization NoiseCode1
Activation-Informed Merging of Large Language ModelsCode1
A Unified Pruning Framework for Vision TransformersCode1
Data-Free Network Quantization With Adversarial Knowledge DistillationCode1
BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover's DistanceCode1
Deep Compression for PyTorch Model Deployment on MicrocontrollersCode1
Contrastive Representation DistillationCode1
Contrastive Distillation on Intermediate Representations for Language Model CompressionCode1
CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN ExecutionCode1
Show:102550
← PrevPage 3 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