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 351–400 of 1356 papers

TitleStatusHype
Image Classification with CondenseNeXt for ARM-Based Computing PlatformsCode0
I3D: Transformer architectures with input-dependent dynamic depth for speech recognitionCode0
Is Modularity Transferable? A Case Study through the Lens of Knowledge DistillationCode0
A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNsCode0
Cross-lingual Distillation for Text ClassificationCode0
HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model CompressionCode0
Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMsCode0
HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge DistillationCode0
High-fidelity 3D Model Compression based on Key SpheresCode0
A Computing Kernel for Network Binarization on PyTorchCode0
Attacking Compressed Vision TransformersCode0
Bayesian Optimization with Clustering and Rollback for CNN Auto PruningCode0
Bayesian Tensorized Neural Networks with Automatic Rank SelectionCode0
Model compression as constrained optimization, with application to neural nets. Part V: combining compressionsCode0
Model Compression for Dynamic Forecast CombinationCode0
How does topology of neural architectures impact gradient propagation and model performance?Code0
Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and MemoryCode0
Model Fusion via Optimal TransportCode0
Iterative Filter Pruning for Concatenation-based CNN ArchitecturesCode0
Differentially Private Knowledge Distillation via Synthetic Text GenerationCode0
CA-LoRA: Adapting Existing LoRA for Compressed LLMs to Enable Efficient Multi-Tasking on Personal DevicesCode0
Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural NetworksCode0
“Learning-Compression” Algorithms for Neural Net PruningCode0
Group channel pruning and spatial attention distilling for object detectionCode0
Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM CompressionCode0
COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language ModelsCode0
Generalizing Teacher Networks for Effective Knowledge Distillation Across Student ArchitecturesCode0
COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level PruningCode0
GSB: Group Superposition Binarization for Vision Transformer with Limited Training SamplesCode0
Foundations of Large Language Model Compression -- Part 1: Weight QuantizationCode0
Asymmetric Masked Distillation for Pre-Training Small Foundation ModelsCode0
From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model CompressionCode0
GASL: Guided Attention for Sparsity Learning in Deep Neural NetworksCode0
FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model CompressionCode0
FLoCoRA: Federated learning compression with low-rank adaptationCode0
JavaScript Convolutional Neural Networks for Keyword Spotting in the Browser: An Experimental AnalysisCode0
Finding Deviated Behaviors of the Compressed DNN Models for Image ClassificationsCode0
Distilling Model KnowledgeCode0
A flexible, extensible software framework for model compression based on the LC algorithmCode0
Lottery Aware Sparsity Hunting: Enabling Federated Learning on Resource-Limited EdgeCode0
Computer Vision Model Compression Techniques for Embedded Systems: A SurveyCode0
Fast DistilBERT on CPUsCode0
StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNsCode0
PENNI: Pruned Kernel Sharing for Efficient CNN InferenceCode0
Faithful Label-free Knowledge DistillationCode0
Physics Inspired Criterion for Pruning-Quantization Joint LearningCode0
FedSynth: Gradient Compression via Synthetic Data in Federated LearningCode0
PocketFlow: An Automated Framework for Compressing and Accelerating Deep Neural NetworksCode0
Explicit-NeRF-QA: A Quality Assessment Database for Explicit NeRF Model CompressionCode0
Exploiting Kernel Sparsity and Entropy for Interpretable CNN CompressionCode0
Show:102550
← PrevPage 8 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