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 1301–1350 of 1356 papers

TitleStatusHype
ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer AccelerationCode0
Preserved central model for faster bidirectional compression in distributed settingsCode0
Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated LearningCode0
ML Research BenchmarkCode0
Einconv: Exploring Unexplored Tensor Network Decompositions for Convolutional Neural NetworksCode0
Self-Supervised Learning from Contrastive Mixtures for Personalized Speech EnhancementCode0
A Miniaturized Semantic Segmentation Method for Remote Sensing ImageCode0
Efficient Speech Translation through Model Compression and Knowledge DistillationCode0
Adversarial Robustness vs. Model Compression, or Both?Code0
Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMMCode0
Data-Free Knowledge Distillation for Image Super-ResolutionCode0
Semi-Online Knowledge DistillationCode0
Understanding the Role of Mixup in Knowledge Distillation: An Empirical StudyCode0
Data-free Knowledge Distillation for Fine-grained Visual CategorizationCode0
Data-Free Backbone Fine-Tuning for Pruned Neural NetworksCode0
Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI FeedbackCode0
RanDeS: Randomized Delta Superposition for Multi-Model CompressionCode0
SymbolNet: Neural Symbolic Regression with Adaptive Dynamic Pruning for CompressionCode0
Model Compression for Domain Adaptation through Causal Effect EstimationCode0
Model Compression for Dynamic Forecast CombinationCode0
On Model Compression for Neural Networks: Framework, Algorithm, and Convergence GuaranteeCode0
Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision TransformerCode0
Shakeout: A New Approach to Regularized Deep Neural Network TrainingCode0
Shapeshifter: a Parameter-efficient Transformer using Factorized Reshaped MatricesCode0
Model Compression Techniques in Biometrics Applications: A SurveyCode0
Systematic Outliers in Large Language ModelsCode0
Pruning by Explaining: A Novel Criterion for Deep Neural Network PruningCode0
Model compression via distillation and quantizationCode0
Data-Free Adversarial DistillationCode0
Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-TuningCode0
Teacher-Student Compression with Generative Adversarial NetworksCode0
Change Is the Only Constant: Dynamic LLM Slicing based on Layer RedundancyCode0
Cross-lingual Distillation for Text ClassificationCode0
Class-dependent Compression of Deep Neural NetworksCode0
Efficient model compression with Random Operation Access Specific Tile (ROAST) hashingCode0
CA-LoRA: Adapting Existing LoRA for Compressed LLMs to Enable Efficient Multi-Tasking on Personal DevicesCode0
Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devicesCode0
Model Fusion via Optimal TransportCode0
COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language ModelsCode0
Model Slicing for Supporting Complex Analytics with Elastic Inference Cost and Resource ConstraintsCode0
Causal Explanation of Convolutional Neural NetworksCode0
A Brief Review of Hypernetworks in Deep LearningCode0
COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level PruningCode0
Actor-Mimic: Deep Multitask and Transfer Reinforcement LearningCode0
Simple is what you need for efficient and accurate medical image segmentationCode0
Computer Vision Model Compression Techniques for Embedded Systems: A SurveyCode0
Multi-Dimensional Model Compression of Vision TransformerCode0
QIANets: Quantum-Integrated Adaptive Networks for Reduced Latency and Improved Inference Times in CNN ModelsCode0
Multi-Granularity Structural Knowledge Distillation for Language Model CompressionCode0
Weightless: Lossy Weight Encoding For Deep Neural Network CompressionCode0
Show:102550
← PrevPage 27 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