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 151–200 of 1356 papers

TitleStatusHype
Consistent Quantity-Quality Control across Scenes for Deployment-Aware Gaussian SplattingCode1
Towards Compact Neural Networks via End-to-End Training: A Bayesian Tensor Approach with Automatic Rank DeterminationCode1
Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained DevicesCode1
EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary SearchCode1
Aligned Structured Sparsity Learning for Efficient Image Super-ResolutionCode1
Faster and Lighter LLMs: A Survey on Current Challenges and Way ForwardCode1
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware TransformationCode1
FedUKD: Federated UNet Model with Knowledge Distillation for Land Use Classification from Satellite and Street ViewsCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
A Unified Pruning Framework for Vision TransformersCode1
General Instance Distillation for Object DetectionCode1
Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural NetworksCode1
Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement LearningCode1
CompRess: Self-Supervised Learning by Compressing RepresentationsCode1
Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-Constrained Edge Computing SystemsCode1
HiNeRV: Video Compression with Hierarchical Encoding-based Neural RepresentationCode1
Compression-Aware Video Super-ResolutionCode1
Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient DetectorsCode1
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer ProgrammingCode1
Initialization and Regularization of Factorized Neural LayersCode1
Activation-Informed Merging of Large Language ModelsCode1
A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution RobustnessCode1
Computation-Efficient Knowledge Distillation via Uncertainty-Aware MixupCode1
Backdoor Attacks on Federated Learning with Lottery Ticket HypothesisCode1
CHEX: CHannel EXploration for CNN Model CompressionCode1
Learned Step Size QuantizationCode1
Contrastive Distillation on Intermediate Representations for Language Model CompressionCode1
Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model CompressionCode1
Comprehensive Knowledge Distillation with Causal InterventionCode1
Composable Interventions for Language ModelsCode1
LiMuSE: Lightweight Multi-modal Speaker ExtractionCode1
LiteYOLO-ID: A Lightweight Object Detection Network for Insulator Defect DetectionCode1
"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel ApproachCode1
BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover's DistanceCode1
Streamlining Redundant Layers to Compress Large Language ModelsCode1
Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse NetworkCode1
Merging Feed-Forward Sublayers for Compressed TransformersCode1
DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model GeneralizationCode1
Compacting, Picking and Growing for Unforgetting Continual LearningCode1
Bidirectional Distillation for Top-K Recommender SystemCode1
Contrastive Representation DistillationCode1
DiSparse: Disentangled Sparsification for Multitask Model CompressionCode1
Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and PruningCode1
Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic HashingCode1
An Efficient Multilingual Language Model Compression through Vocabulary TrimmingCode1
Passport-aware Normalization for Deep Model ProtectionCode1
Performance-aware Approximation of Global Channel Pruning for Multitask CNNsCode1
Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image RecognitionCode1
Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated LearningCode1
Gaussian RAM: Lightweight Image Classification via Stochastic Retina-Inspired Glimpse and Reinforcement LearningCode1
Show:102550
← PrevPage 4 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