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 701–750 of 1356 papers

TitleStatusHype
Learning to Collide: Recommendation System Model Compression with Learned Hash Functions—0
Model LEGO: Creating Models Like Disassembling and Assembling Building BlocksCode1
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal—0
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and QuantizationCode1
Compression of Generative Pre-trained Language Models via Quantization—0
PublicCheck: Public Integrity Verification for Services of Run-time Deep Models—0
Learning Compressed Embeddings for On-Device Inference—0
A Closer Look at Knowledge Distillation with Features, Logits, and Gradients—0
Approximability and Generalisation—0
A Mixed Integer Programming Approach for Verifying Properties of Binarized Neural Networks—0
An Empirical Study of Low Precision Quantization for TinyML—0
Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance—0
Structured Pruning is All You Need for Pruning CNNs at Initialization—0
E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models—0
KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models—0
Multi-task Learning Approach for Modulation and Wireless Signal Classification for 5G and Beyond: Edge Deployment via Model Compression—0
A Novel Architecture Slimming Method for Network Pruning and Knowledge Distillation—0
Time-Correlated Sparsification for Efficient Over-the-Air Model Aggregation in Wireless Federated Learning—0
A Survey on Model Compression and Acceleration for Pretrained Language Models—0
SPDY: Accurate Pruning with Speedup GuaranteesCode1
Memory-Efficient Backpropagation through Large Linear LayersCode1
Training Thinner and Deeper Neural Networks: Jumpstart RegularizationCode0
AutoMC: Automated Model Compression based on Domain Knowledge and Progressive search strategyCode0
Enabling Deep Learning on Edge Devices through Filter Pruning and Knowledge Transfer—0
Can Model Compression Improve NLP Fairness—0
AutoDistill: an End-to-End Framework to Explore and Distill Hardware-Efficient Language Models—0
High-fidelity 3D Model Compression based on Key SpheresCode0
PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting—0
UDC: Unified DNAS for Compressible TinyML Models—0
DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI ScaleCode0
ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce ConnectionsCode0
Two-Pass End-to-End ASR Model Compression—0
The Effect of Model Compression on Fairness in Facial Expression Recognition—0
Dreaming To Prune Image Deraining Networks—0
HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks—0
Croesus: Multi-Stage Processing and Transactions for Video-Analytics in Edge-Cloud Systems—0
Multi-Dimensional Model Compression of Vision TransformerCode0
Conditional Generative Data-free Knowledge Distillation—0
Data-Free Knowledge Transfer: A Survey—0
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural NetworksCode1
Automatic Mixed-Precision Quantization Search of BERT—0
SPViT: Enabling Faster Vision Transformers via Soft Token PruningCode1
LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision—0
Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image RecognitionCode1
From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model CompressionCode0
Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation—0
Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularization—0
Finding Deviated Behaviors of the Compressed DNN Models for Image ClassificationsCode0
Toward Real-World Voice Disorder Classification—0
Shapeshifter: a Parameter-efficient Transformer using Factorized Reshaped MatricesCode0
Show:102550
← PrevPage 15 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