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 351–375 of 1356 papers

TitleStatusHype
Bayesian Optimization with Clustering and Rollback for CNN Auto PruningCode0
A Computing Kernel for Network Binarization on PyTorchCode0
Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural NetworksCode0
Attacking Compressed Vision TransformersCode0
GSB: Group Superposition Binarization for Vision Transformer with Limited Training SamplesCode0
High-fidelity 3D Model Compression based on Key SpheresCode0
CA-LoRA: Adapting Existing LoRA for Compressed LLMs to Enable Efficient Multi-Tasking on Personal DevicesCode0
GASL: Guided Attention for Sparsity Learning in Deep Neural NetworksCode0
From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model CompressionCode0
COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language ModelsCode0
FLoCoRA: Federated learning compression with low-rank adaptationCode0
COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level PruningCode0
FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model CompressionCode0
ML Research BenchmarkCode0
Foundations of Large Language Model Compression -- Part 1: Weight QuantizationCode0
Generalizing Teacher Networks for Effective Knowledge Distillation Across Student ArchitecturesCode0
Asymmetric Masked Distillation for Pre-Training Small Foundation ModelsCode0
Teacher-Student Compression with Generative Adversarial NetworksCode0
Few Shot Network Compression via Cross DistillationCode0
Differentially Private Knowledge Distillation via Synthetic Text GenerationCode0
Lottery Aware Sparsity Hunting: Enabling Federated Learning on Resource-Limited EdgeCode0
Finding Deviated Behaviors of the Compressed DNN Models for Image ClassificationsCode0
Explicit-NeRF-QA: A Quality Assessment Database for Explicit NeRF Model CompressionCode0
Exact Backpropagation in Binary Weighted Networks with Group Weight TransformationsCode0
Exploiting Kernel Sparsity and Entropy for Interpretable CNN CompressionCode0
Show:102550
← PrevPage 15 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