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 51–100 of 1356 papers

TitleStatusHype
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
DiSparse: Disentangled Sparsification for Multitask Model CompressionCode1
Faster and Lighter LLMs: A Survey on Current Challenges and Way ForwardCode1
FFNeRV: Flow-Guided Frame-Wise Neural Representations for VideosCode1
FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix ApproximationCode1
Forget the Data and Fine-Tuning! Just Fold the Network to CompressCode1
Gaussian RAM: Lightweight Image Classification via Stochastic Retina-Inspired Glimpse and Reinforcement LearningCode1
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and QuantizationCode1
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
Global Sparse Momentum SGD for Pruning Very Deep Neural NetworksCode1
DE-RRD: A Knowledge Distillation Framework for Recommender SystemCode1
Densely Guided Knowledge Distillation using Multiple Teacher AssistantsCode1
Discovering Dynamic Patterns from Spatiotemporal Data with Time-Varying Low-Rank AutoregressionCode1
DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and TransformersCode1
DarwinLM: Evolutionary Structured Pruning of Large Language ModelsCode1
Contrastive Representation DistillationCode1
CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN ExecutionCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
Computation-Efficient Knowledge Distillation via Uncertainty-Aware MixupCode1
Contrastive Distillation on Intermediate Representations for Language Model CompressionCode1
Data-Free Network Quantization With Adversarial Knowledge DistillationCode1
Dual Relation Knowledge Distillation for Object DetectionCode1
Composable Interventions for Language ModelsCode1
Aligned Structured Sparsity Learning for Efficient Image Super-ResolutionCode1
Comprehensive Knowledge Distillation with Causal InterventionCode1
Compacting, Picking and Growing for Unforgetting Continual LearningCode1
Streamlining Redundant Layers to Compress Large Language ModelsCode1
CompRess: Self-Supervised Learning by Compressing RepresentationsCode1
Consistent Quantity-Quality Control across Scenes for Deployment-Aware Gaussian SplattingCode1
Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer InferenceCode1
Communication-Computation Trade-Off in Resource-Constrained Edge InferenceCode1
COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision ModelsCode1
Activation-Informed Merging of Large Language ModelsCode1
CrossKD: Cross-Head Knowledge Distillation for Object DetectionCode1
An Information Theory-inspired Strategy for Automatic Network PruningCode1
Deep Compression for PyTorch Model Deployment on MicrocontrollersCode1
Communication-Efficient Diffusion Strategy for Performance Improvement of Federated Learning with Non-IID DataCode1
Differentiable Model Compression via Pseudo Quantization NoiseCode1
Discrimination-aware Channel Pruning for Deep Neural NetworksCode1
Discrimination-aware Network Pruning for Deep Model CompressionCode1
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time SystemsCode1
Distilling Linguistic Context for Language Model CompressionCode1
Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded DevicesCode1
Dynamic Slimmable NetworkCode1
An Efficient Multilingual Language Model Compression through Vocabulary TrimmingCode1
Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and BetterCode1
Model LEGO: Creating Models Like Disassembling and Assembling Building BlocksCode1
Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated LearningCode1
Show:102550
← PrevPage 2 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