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 851–900 of 1356 papers

TitleStatusHype
Semi-Online Knowledge DistillationCode0
Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration—0
Local-Selective Feature Distillation for Single Image Super-Resolution—0
Structured Pruning Learns Compact and Accurate Models—0
Weight Squeezing: Reparameterization for Knowledge Transfer and Model Compression—0
Learning-Based Symbol Level Precoding: A Memory-Efficient Unsupervised Learning Approach—0
Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization—0
Learning Interpretation with Explainable Knowledge Distillation—0
SEOFP-NET: Compression and Acceleration of Deep Neural Networks for Speech Enhancement Using Sign-Exponent-Only Floating-Points—0
A Survey on Green Deep Learning—0
Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models—0
Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators—0
How to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding—0
ILMPQ : An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA—0
On Cross-Layer Alignment for Model Fusion of Heterogeneous Neural Networks—0
Reconstructing Pruned Filters using Cheap Spatial Transformations—0
Exploring Gradient Flow Based Saliency for DNN Model CompressionCode0
How and When Adversarial Robustness Transfers in Knowledge Distillation?—0
Analysis of memory consumption by neural networks based on hyperparameters—0
Augmenting Knowledge Distillation With Peer-To-Peer Mutual Learning For Model Compression—0
Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization—0
HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model CompressionCode0
A Short Study on Compressing Decoder-Based Language Models—0
Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding—0
Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher—0
Kronecker Decomposition for GPT Compression—0
Differentiable Network Pruning for Microcontrollers—0
A Memory-Efficient Learning Framework for SymbolLevel Precoding with Quantized NN Weights—0
Rectifying the Data Bias in Knowledge Distillation—0
FedDQ: Communication-Efficient Federated Learning with Descending Quantization—0
KIMERA: Injecting Domain Knowledge into Vacant Transformer Heads—0
A Unified Knowledge Distillation Framework for Deep Directed Graphical Models—0
Sparse Unbalanced GAN Training with In-Time Over-Parameterization—0
HFSP: A Hardware-friendly Soft Pruning Framework for Vision Transformers—0
Model Compression via Symmetries of the Parameter Space—0
Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning—0
Robot Intent Recognition Method Based on State Grid Business Office—0
Prototypical Contrastive Predictive Coding—0
Bayesian Optimization with Clustering and Rollback for CNN Auto PruningCode0
Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications—0
Experimental implementation of a neural network optical channel equalizer in restricted hardware using pruning and quantization—0
A Note on Knowledge Distillation Loss Function for Object Classification—0
Multihop: Leveraging Complex Models to Learn Accurate Simple Models—0
KroneckerBERT: Learning Kronecker Decomposition for Pre-trained Language Models via Knowledge Distillation—0
Causal Explanation of Convolutional Neural NetworksCode0
BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables—0
GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization—0
Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision—0
Lipschitz Continuity Guided Knowledge Distillation—0
DKM: Differentiable K-Means Clustering Layer for Neural Network Compression—0
Show:102550
← PrevPage 18 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