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 3301–3350 of 4925 papers

TitleStatusHype
Optimization of Quantized Phase Shifts for Reconfigurable Smart Surfaces Assisted Communications—0
Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression—0
End-to-End Learned Image Compression with Quantized Weights and Activations—0
Low Precision Decentralized Distributed Training over IID and non-IID DataCode0
Reconstruction-Computation-Quantization (RCQ): A Paradigm for Low Bit Width LDPC Decoding—0
Online Meta Adaptation for Variable-Rate Learned Image Compression—0
VQN: Variable Quantization Noise for Neural Network Compression—0
Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking—0
Wyner-Ziv Gradient Compression for Federated Learning—0
Predicting Attention Sparsity in Transformers—0
On the Tradeoff between Energy, Precision, and Accuracy in Federated Quantized Neural Networks—0
Machine Learning for CSI Recreation Based on Prior Knowledge—0
Energy Efficient Learning with Low Resolution Stochastic Domain Wall Synapse Based Deep Neural Networks—0
Iterative Training: Finding Binary Weight Deep Neural Networks with Layer BinarizationCode0
A Robust Deep Learning-Based Beamforming Design for RIS-assisted Multiuser MISO Communications with Practical Constraints—0
Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization—0
Q-Learning for MDPs with General Spaces: Convergence and Near Optimality via Quantization under Weak Continuity—0
Solving Multi-Arm Bandit Using a Few Bits of Communication—0
Variability-Aware Training and Self-Tuning of Highly Quantized DNNs for Analog PIM—0
An Underexplored Dilemma between Confidence and Calibration in Quantized Neural NetworksCode0
Prune Once for All: Sparse Pre-Trained Language Models—0
Entropy optimized semi-supervised decomposed vector-quantized variational autoencoder model based on transfer learning for multiclass text classification and generation—0
Graph-Based Depth Denoising & Dequantization for Point Cloud Enhancement—0
Learning from Multiple Time Series: A Deep Disentangled Approach to Diversified Time Series Forecasting—0
Differential Modulation in Massive MIMO With Low-Resolution ADCs—0
ML-EXray: Visibility into ML Deployment on the Edge—0
Rethinking Deconvolution for 2D Human Pose Estimation Light yet Accurate Model for Real-time Edge Computing—0
LW-GCN: A Lightweight FPGA-based Graph Convolutional Network Accelerator—0
Constructing High-Order Signed Distance Maps from Computed Tomography Data with Application to Bone Morphometry—0
Simple and Effective Unsupervised Redundancy Elimination to Compress Dense Vectors for Passage Retrieval—0
Structure Information is the Key: Self-Attention RoI Feature Extractor in 3D Object Detection—0
HW-TSC’s Participation in the WMT 2021 Efficiency Shared Task—0
PP-ShiTu: A Practical Lightweight Image Recognition SystemCode0
Efficient Machine Translation with Model Pruning and Quantization—0
Revealing and Protecting Labels in Distributed TrainingCode0
Reconfigurable Intelligent Surface-induced Randomness for mmWave Key Generation—0
DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning—0
ILMPQ : An Intra-Layer Multi-Precision Deep Neural Network Quantization framework for FPGA—0
RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions—0
Nash equilibrium of multi-agent graphical game with a privacy information encrypted learning algorithm—0
FAST: DNN Training Under Variable Precision Block Floating Point with Stochastic Rounding—0
MERCURY: Accelerating DNN Training By Exploiting Input Similarity—0
Differential Deep Detection in Massive MIMO With One-Bit ADC—0
High-Order Signed Distance Transform of Sampled Signals—0
Algorithms for the Communication of Samples—0
Demystifying and Generalizing BinaryConnect—0
Deep Asymmetric Hashing with Dual Semantic Regression and Class Structure Quantization—0
Task-Based Graph Signal CompressionCode0
A Layer-wise Adversarial-aware Quantization Optimization for Improving Robustness—0
Vis-TOP: Visual Transformer Overlay Processor—0
Show:102550
← PrevPage 67 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