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 2351–2400 of 4925 papers

TitleStatusHype
Summary Statistic Privacy in Data SharingCode0
Ultra-low Power Deep Learning-based Monocular Relative Localization Onboard Nano-quadrotors—0
Ternary Quantization: A Survey—0
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages—0
Boosting Distributed Full-graph GNN Training with Asynchronous One-bit Communication—0
Comprehensive Comparisons of Uniform Quantization in Deep Image CompressionCode0
A Probabilistic Reformulation Technique for Discrete RIS Optimization in Wireless Systems—0
Ultra-low Precision Multiplication-free Training for Deep Neural Networks—0
Wireless End-to-End Image Transmission System using Semantic Communications—0
The Effect of Points Dispersion on the k-nn Search in Random Projection ForestsCode0
JND-Based Perceptual Optimization For Learned Image Compression—0
Raw Image Reconstruction with Learned Compact MetadataCode1
DyBit: Dynamic Bit-Precision Numbers for Efficient Quantized Neural Network Inference—0
Vision-Language Generative Model for View-Specific Chest X-ray GenerationCode1
Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision TransformersCode0
Refining a k-nearest neighbor graph for a computationally efficient spectral clusteringCode0
HDR image watermarking using saliency detection and quantization index modulation—0
Approximate spectral clustering density-based similarity for noisy datasetsCode0
Quantized Low-Rank Multivariate Regression with Random Dithering—0
Optical Transformers—0
Fixflow: A Framework to Evaluate Fixed-point Arithmetic in Light-Weight CNN Inference—0
Rethinking Data-Free Quantization as a Zero-Sum GameCode0
Evaluation of Linear Implicit Quantized State System method for analyzing mission performance of power systems—0
An anatomy-based V1 model: Extraction of Low-level Features, Reduction of distortion and a V1-inspired SOM—0
LiQuiD-MIMO Radar: Distributed MIMO Radar with Low-Bit Quantization—0
QARV: Quantization-Aware ResNet VAE for Lossy Image CompressionCode1
Speech Enhancement with Multi-granularity Vector Quantization—0
With Shared Microexponents, A Little Shifting Goes a Long WayCode1
Towards Optimal Compression: Joint Pruning and Quantization—0
Sparse-SignSGD with Majority Vote for Communication-Efficient Distributed Learning—0
PolyFormer: Referring Image Segmentation as Sequential Polygon GenerationCode1
SEAM: Searching Transferable Mixed-Precision Quantization Policy through Large Margin Regularization—0
gpcgc: a green point cloud geometry coding method—0
Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data—0
Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text AttacksCode0
A Practical Mixed Precision Algorithm for Post-Training Quantization—0
Binarized Neural Machine TranslationCode2
Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learning—0
ASTRIDE: Adaptive Symbolization for Time Series DatabasesCode1
The Hardware Impact of Quantization and Pruning for Weights in Spiking Neural NetworksCode1
Q-Diffusion: Quantizing Diffusion ModelsCode2
Quantized Distributed Training of Large Models with Convergence Guarantees—0
Oscillation-free Quantization for Low-bit Vision TransformersCode1
Knowledge Distillation in Vision Transformers: A Critical Review—0
Mixed Precision Post Training Quantization of Neural Networks with Sensitivity Guided Search—0
QCM-SGM+: Improved Quantized Compressed Sensing With Score-Based Generative ModelsCode1
UW-CVGAN: UnderWater Image Enhancement with Capsules Vectors Quantization—0
Disco Intelligent Reflecting Surfaces: Active Channel Aging for Fully-Passive Jamming Attacks—0
A^2Q: Aggregation-Aware Quantization for Graph Neural NetworksCode1
Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance—0
Show:102550
← PrevPage 48 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