SOTAVerified

Quantization

Quantization is a promising technique to reduce the computation cost of neural network training, which can replace high-cost floating-point numbers (e.g., float32) with low-cost fixed-point numbers (e.g., int8/int16).

Source: Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 3551–3600 of 4925 papers

TitleStatusHype
Computational data analysis for first quantization estimation on JPEG double compressed imagesCode0
Quantization optimized with respect to the Haar basis—0
Who's a Good Boy? Reinforcing Canine Behavior in Real-Time using Machine LearningCode0
Noise Sensitivity-Based Energy Efficient and Robust Adversary Detection in Neural Networks—0
I-BERT: Integer-only BERT QuantizationCode2
Improving Low-Precision Network Quantization via Bin Regularization—0
Uniformity in Heterogeneity: Diving Deep Into Count Interval Partition for Crowd CountingCode1
RangeDet: In Defense of Range View for LiDAR-Based 3D Object DetectionCode1
Product Quantizer Aware Inverted Index for Scalable Nearest Neighbor Search—0
Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-PointCode1
Practical Locally Private Federated Learning with Communication Efficiency—0
Explore the Potential of CNN Low Bit Training—0
Incremental few-shot learning via vector quantization in deep embedded space—0
Post-Training Weighted Quantization of Neural Networks for Language Models—0
WrapNet: Neural Net Inference with Ultra-Low-Precision Arithmetic—0
Multi-Prize Lottery Ticket Hypothesis: Finding Generalizable and Efficient Binary Subnetworks in a Randomly Weighted Neural Network—0
Uniform-Precision Neural Network Quantization via Neural Channel Expansion—0
TwinDNN: A Tale of Two Deep Neural Networks—0
Weights Having Stable Signs Are Important: Finding Primary Subnetworks and Kernels to Compress Binary Weight Networks—0
Improving the accuracy of neural networks in analog computing-in-memory systems by a generalized quantization method—0
End-to-end Quantized Training via Log-Barrier Extensions—0
WAVEQ: GRADIENT-BASED DEEP QUANTIZATION OF NEURAL NETWORKS THROUGH SINUSOIDAL REGULARIZATIONCode0
Simple Augmentation Goes a Long Way: ADRL for DNN Quantization—0
Semi-Relaxed Quantization with DropBits: Training Low-Bit Neural Networks via Bitwise Regularization—0
Hybrid and Non-Uniform DNN quantization methods using Retro Synthesis data for efficient inference—0
DQSGD: DYNAMIC QUANTIZED STOCHASTIC GRADIENT DESCENT FOR COMMUNICATION-EFFICIENT DISTRIBUTED LEARNING—0
Collaborative Filtering with Smooth Reconstruction of the Preference Function—0
Learned Multi-Resolution Variable-Rate Image Compression with Octave-based Residual Blocks—0
BinaryBERT: Pushing the Limit of BERT Quantization—0
A Memory Efficient Baseline for Open Domain Question AnsweringCode1
Improving Adversarial Robustness in Weight-quantized Neural Networks—0
Hybrid and Non-Uniform quantization methods using retro synthesis data for efficient inference—0
Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks—0
Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal HashingCode1
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN TrainingCode1
EQ-Net: A Unified Deep Learning Framework for Log-Likelihood Ratio Estimation and Quantization—0
Energy Efficient Federated Learning over Heterogeneous Mobile Devices via Joint Design of Weight Quantization and Wireless Transmission—0
DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution NetworksCode1
Study of Energy-Efficient Distributed RLS-based Learning with Coarsely Quantized Signals—0
One-Bit Target Detection in Collocated MIMO Radar and Performance Degradation Analysis—0
Resource-efficient DNNs for Keyword Spotting using Neural Architecture Search and QuantizationCode0
FantastIC4: A Hardware-Software Co-Design Approach for Efficiently Running 4bit-Compact Multilayer Perceptrons—0
SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning—0
Efficient CNN-LSTM based Image Captioning using Neural Network CompressionCode0
CosSGD: Communication-Efficient Federated Learning with a Simple Cosine-Based Quantization—0
Exploring Neural Networks Quantization via Layer-Wise Quantization Analysis—0
Scalable Verification of Quantized Neural Networks (Technical Report)Code0
Robust Downlink Transmit Optimization under Quantized Channel Feedback via the Strong Duality for QCQP—0
Quantizing data for distributed learning—0
Predicting Generalization in Deep Learning via Local Measures of Distortion—0
Show:102550
← PrevPage 72 of 99Next →
All datasetsImageNetCIFAR-10Wiki-40BAgeDB-30CFP-FPCOCO (Common Objects in Context)IJB-BIJB-CKnowledge-based:LFW

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FQ-ViT (ViT-L)Top-1 Accuracy (%)85.03—Unverified
2FQ-ViT (ViT-B)Top-1 Accuracy (%)83.31—Unverified
3FQ-ViT (Swin-B)Top-1 Accuracy (%)82.97—Unverified
4FQ-ViT (Swin-S)Top-1 Accuracy (%)82.71—Unverified
5FQ-ViT (DeiT-B)Top-1 Accuracy (%)81.2—Unverified
6FQ-ViT (Swin-T)Top-1 Accuracy (%)80.51—Unverified
7FQ-ViT (DeiT-S)Top-1 Accuracy (%)79.17—Unverified
8Xception W8A8Top-1 Accuracy (%)78.97—Unverified
9ADLIK-MO-ResNet50-W4A4Top-1 Accuracy (%)77.88—Unverified
10ADLIK-MO-ResNet50-W3A4Top-1 Accuracy (%)77.34—Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_3MAP160,327.04—Unverified
2DTQMAP0.79—Unverified
#ModelMetricClaimedVerifiedStatus
1OutEffHop-Bert_basePerplexity6.3—Unverified
2OutEffHop-Bert_basePerplexity6.21—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy98.13—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy92.92—Unverified
#ModelMetricClaimedVerifiedStatus
1SSD ResNet50 V1 FPN 640x640MAP34.3—Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-495.13—Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-496.38—Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_5All84,809,664—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy99.8—Unverified