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 626–650 of 1356 papers

TitleStatusHype
Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference—0
SwiftPrune: Hessian-Free Weight Pruning for Large Language Models—0
D^2MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving—0
FoldGPT: Simple and Effective Large Language Model Compression Scheme—0
DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks—0
ICD-Face: Intra-class Compactness Distillation for Face Recognition—0
Identifying Sub-networks in Neural Networks via Functionally Similar Representations—0
ILMPQ : An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA—0
DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer—0
FLOPs as a Direct Optimization Objective for Learning Sparse Neural Networks—0
Impact of Disentanglement on Pruning Neural Networks—0
Implicit Neural Representation for Videos Based on Residual Connection—0
A Survey on Drowsiness Detection -- Modern Applications and Methods—0
Computation-efficient Deep Learning for Computer Vision: A Survey—0
A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation—0
Improve Knowledge Distillation via Label Revision and Data Selection—0
Interpreting Deep Classifier by Visual Distillation of Dark Knowledge—0
Intrinsically Sparse Long Short-Term Memory Networks—0
Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning—0
Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing—0
FlatENN: Train Flat for Enhanced Fault Tolerance of Quantized Deep Neural Networks—0
FIT: A Metric for Model Sensitivity—0
In defense of parameter sharing for model-compression—0
Individual Content and Motion Dynamics Preserved Pruning for Video Diffusion Models—0
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead—0
Show:102550
← PrevPage 26 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