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 201–250 of 1356 papers

TitleStatusHype
Learning Efficient Vision Transformers via Fine-Grained Manifold DistillationCode1
Search for Efficient Large Language ModelsCode1
Skip-Convolutions for Efficient Video ProcessingCode1
SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight CompressionCode1
An Empirical Study of CLIP for Text-based Person SearchCode1
SPDY: Accurate Pruning with Speedup GuaranteesCode1
Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-PointCode1
Consistent Quantity-Quality Control across Scenes for Deployment-Aware Gaussian SplattingCode1
PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt TuningCode1
Artemis: HE-Aware Training for Efficient Privacy-Preserving Machine Learning—0
Are We There Yet? A Measurement Study of Efficiency for LLM Applications on Mobile Devices—0
Accelerating Very Deep Convolutional Networks for Classification and Detection—0
A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques—0
Accelerating Machine Learning Primitives on Commodity Hardware—0
Compositionality Unlocks Deep Interpretable Models—0
CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting—0
Complexity-Driven CNN Compression for Resource-constrained Edge AI—0
Architecture Compression—0
A Progressive Sub-Network Searching Framework for Dynamic Inference—0
Compact CNN Structure Learning by Knowledge Distillation—0
A Deep Cascade Network for Unaligned Face Attribute Classification—0
Continuous Approximations for Improving Quantization Aware Training of LLMs—0
Convolutional Neural Network Compression Based on Low-Rank Decomposition—0
Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity—0
A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework—0
2-bit Conformer quantization for automatic speech recognition—0
Approximability and Generalisation—0
CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders—0
Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy—0
Additive Tree-Structured Covariance Function for Conditional Parameter Spaces in Bayesian Optimization—0
Collaborative Teacher-Student Learning via Multiple Knowledge Transfer—0
ADC/DAC-Free Analog Acceleration of Deep Neural Networks with Frequency Transformation—0
Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization—0
Applications of Knowledge Distillation in Remote Sensing: A Survey—0
Communication-Efficient Distributed Online Learning with Kernels—0
Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization—0
Communication-Efficient Federated Learning with Adaptive Compression under Dynamic Bandwidth—0
ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning—0
A Partial Regularization Method for Network Compression—0
Closed-Loop Neural Interfaces with Embedded Machine Learning—0
CompactifAI: Extreme Compression of Large Language Models using Quantum-Inspired Tensor Networks—0
Compacting Deep Neural Networks for Internet of Things: Methods and Applications—0
Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications—0
An Overview of Neural Network Compression—0
AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications—0
10K is Enough: An Ultra-Lightweight Binarized Network for Infrared Small-Target Detection—0
Context-aware deep model compression for edge cloud computing—0
Convolutional Neural Network Compression via Dynamic Parameter Rank Pruning—0
A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation—0
Adaptive Learning of Tensor Network Structures—0
Show:102550
← PrevPage 5 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