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 451–475 of 1356 papers

TitleStatusHype
ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning—0
Efficient Memory Management for GPU-based Deep Learning Systems—0
Automatic Block-wise Pruning with Auxiliary Gating Structures for Deep Convolutional Neural Networks—0
Efficient Model Compression for Hierarchical Federated Learning—0
Efficient Model Compression Techniques with FishLeg—0
Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization—0
Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices—0
Data-Independent Structured Pruning of Neural Networks via Coresets—0
Automated Model Compression by Jointly Applied Pruning and Quantization—0
Efficient Pruning of Text-to-Image Models: Insights from Pruning Stable Diffusion—0
AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models—0
Data-Free Quantization via Pseudo-label Filtering—0
Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning—0
Efficient Speech Representation Learning with Low-Bit Quantization—0
Automated Inference of Graph Transformation Rules—0
Efficient Supernet Training with Orthogonal Softmax for Scalable ASR Model Compression—0
Data-Free Knowledge Transfer: A Survey—0
Auto Graph Encoder-Decoder for Neural Network Pruning—0
A Low-Power Streaming Speech Enhancement Accelerator For Edge Devices—0
E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models—0
Acoustic Model Compression with MAP adaptation—0
Communication-Efficient Distributed Online Learning with Kernels—0
Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Images—0
Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models—0
AutoDistill: an End-to-End Framework to Explore and Distill Hardware-Efficient Language Models—0
Show:102550
← PrevPage 19 of 55Next →
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