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 901–950 of 1356 papers

TitleStatusHype
Prototype-based Personalized Pruning—0
Dynamic Slimmable NetworkCode1
Compacting Deep Neural Networks for Internet of Things: Methods and Applications—0
Robust Model Compression Using Deep HypothesesCode0
MWQ: Multiscale Wavelet Quantized Neural Networks—0
A Real-time Low-cost Artificial Intelligence System for Autonomous Spraying in Palm PlantationsCode1
Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained DevicesCode1
Formalizing Generalization and Robustness of Neural Networks to Weight Perturbations—0
General Instance Distillation for Object DetectionCode1
On the Utility of Gradient Compression in Distributed Training SystemsCode0
PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation—0
Preserved central model for faster bidirectional compression in distributed settingsCode0
Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?—0
An Information-Theoretic Justification for Model PruningCode1
Neural Network Compression for Noisy Storage Devices—0
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware TransformationCode1
Robustness in Compressed Neural Networks for Object Detection—0
LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture SearchCode1
Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement LearningCode1
Show, Attend and Distill:Knowledge Distillation via Attention-based Feature MatchingCode1
Compressed Object DetectionCode0
It's always personal: Using Early Exits for Efficient On-Device CNN Personalisation—0
AACP: Model Compression by Accurate and Automatic Channel Pruning—0
Deep Model Compression based on the Training History—0
AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications—0
Differential Privacy Meets Federated Learning under Communication Constraints—0
Collaborative Teacher-Student Learning via Multiple Knowledge Transfer—0
Deep Compression of Neural Networks for Fault Detection on Tennessee Eastman Chemical Processes—0
Model Compression for Domain Adaptation through Causal Effect EstimationCode0
Single-path Bit Sharing for Automatic Loss-aware Model Compression—0
Fast convolutional neural networks on FPGAs with hls4mlCode2
Activation Density based Mixed-Precision Quantization for Energy Efficient Neural Networks—0
Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification—0
On-Device Document Classification using multimodal features—0
Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-PointCode1
Exploration and Estimation for Model Compression—0
Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient DetectorsCode1
Model Compression via Hyper-Structure Network—0
Knowledge distillation via softmax regression representation learning—0
Post-Training Weighted Quantization of Neural Networks for Language Models—0
Task-Agnostic and Adaptive-Size BERT Compression—0
Can Students Outperform Teachers in Knowledge Distillation based Model Compression?—0
SACoD: Sensor Algorithm Co-Design Towards Efficient CNN-powered Intelligent PhlatCamCode0
Block Skim Transformer for Efficient Question Answering—0
A Half-Space Stochastic Projected Gradient Method for Group Sparsity Regularization—0
TwinDNN: A Tale of Two Deep Neural Networks—0
Dynamic Probabilistic Pruning: Training sparse networks based on stochastic and dynamic masking—0
EarlyBERT: Efficient BERT Training via Early-bird Lottery TicketsCode1
BinaryBERT: Pushing the Limit of BERT Quantization—0
Towards Zero-Shot Knowledge Distillation for Natural Language Processing—0
Show:102550
← PrevPage 19 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