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 426–450 of 1356 papers

TitleStatusHype
What is Lost in Knowledge Distillation?—0
Supervised domain adaptation for building extraction from off-nadir aerial images—0
Asymmetric Masked Distillation for Pre-Training Small Foundation ModelsCode0
Data-Free Distillation of Language Model by Text-to-Text Transfer—0
Divergent Token Metrics: Measuring degradation to prune away LLM components -- and optimize quantization—0
Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression—0
LXMERT Model Compression for Visual Question AnsweringCode0
Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Images—0
In defense of parameter sharing for model-compression—0
USDC: Unified Static and Dynamic Compression for Visual Transformer—0
Efficient Apple Maturity and Damage Assessment: A Lightweight Detection Model with GAN and Attention Mechanism—0
What do larger image classifiers memorise?—0
Accelerating Machine Learning Primitives on Commodity Hardware—0
A Corrected Expected Improvement Acquisition Function Under Noisy ObservationsCode0
Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences—0
Robustness-Guided Image Synthesis for Data-Free Quantization—0
Sparse Deep Learning for Time Series Data: Theory and Applications—0
ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models—0
Sweeping Heterogeneity with Smart MoPs: Mixture of Prompts for LLM Task Adaptation—0
Artemis: HE-Aware Training for Efficient Privacy-Preserving Machine Learning—0
Bridging the Gap Between Foundation Models and Heterogeneous Federated Learning—0
Distilling Inductive Bias: Knowledge Distillation Beyond Model Compression—0
CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs—0
On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks "In-the-Wild''—0
VIC-KD: Variance-Invariance-Covariance Knowledge Distillation to Make Keyword Spotting More Robust Against Adversarial Attacks—0
Show:102550
← PrevPage 18 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