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 3601–3650 of 4925 papers

TitleStatusHype
Set-Theoretic Learning for Detection in Cell-Less C-RAN Systems—0
Reduced Precision Strategies for Deep Learning: A High Energy Physics Generative Adversarial Network Use Case—0
Data-free mixed-precision quantization using novel sensitivity metric—0
Learned Gradient Compression for Distributed Deep Learning—0
Efficient Randomized Subspace Embeddings for Distributed Optimization under a Communication BudgetCode0
VMAF-based Bitrate Ladder Estimation for Adaptive Streaming—0
Learnable Companding Quantization for Accurate Low-bit Neural Networks—0
BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networks—0
Quantization-Guided Training for Compact TinyML Models—0
MWQ: Multiscale Wavelet Quantized Neural Networks—0
Wav2vec-C: A Self-supervised Model for Speech Representation Learning—0
Reliability-Aware Quantization for Anti-Aging NPUs—0
Pufferfish: Communication-efficient Models At No Extra CostCode0
Neural Network-based Quantization for Network Automation—0
Deep Neural Network Models Compression—0
Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantization—0
NETWORK COMPRESSION FOR MACHINE-LEARNT FLUID SIMULATIONS—0
Adaptive Transmission for Distributed Detection in Energy Harvesting Wireless Sensor Networks—0
SME: ReRAM-based Sparse-Multiplication-Engine to Squeeze-Out Bit Sparsity of Neural Network—0
Improved Techniques for Quantizing Deep Networks with Adaptive Bit-Widths—0
A Structurally Regularized Convolutional Neural Network for Image Classification using Wavelet-based SubBand Decomposition—0
Diversifying Sample Generation for Accurate Data-Free Quantization—0
SWIS -- Shared Weight bIt Sparsity for Efficient Neural Network Acceleration—0
Human Symmetry Uncertainty Detected by a Self-Organizing Neural Network Map—0
Improving Approximate Optimal Transport Distances using Quantization—0
Quantization Algorithms for Random Fourier Features—0
Fronthaul Compression and Passive Beamforming Design for Intelligent Reflecting Surface-aided Cloud Radio Access Networks—0
FIXAR: A Fixed-Point Deep Reinforcement Learning Platform with Quantization-Aware Training and Adaptive Parallelism—0
QuPeL: Quantized Personalization with Applications to Federated Learning—0
Ps and Qs: Quantization-aware pruning for efficient low latency neural network inferenceCode0
Mixed-Precision Quantization and Parallel Implementation of Multispectral Riemannian Classification for Brain--Machine InterfacesCode0
Multi-Agent Consensus Subject to Communication and Privacy Constraints—0
GradFreeBits: Gradient Free Bit Allocation for Dynamic Low Precision Neural Networks—0
Peering Beyond the Gradient Veil with Distributed Auto Differentiation—0
RFI Mitigation for One-bit UWB Radar Systems—0
An Implementation of Vector Quantization using the Genetic Algorithm Approach—0
The Wavefunction of Continuous-Time Recurrent Neural Networks—0
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure AggregationCode0
Visualizing hierarchies in scRNA-seq data using a density tree-biased autoencoderCode0
Group Quantization of Quadratic Hamiltonians in Finance—0
Distribution Adaptive INT8 Quantization for Training CNNs—0
Sparsification via Compressed Sensing for Automatic Speech Recognition—0
VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference—0
Communication-efficient k-Means for Edge-based Machine Learning—0
Adaptive Quantization of Model Updates for Communication-Efficient Federated Learning—0
Refining a -nearest neighbor graph for a computationally efficient spectral clusteringCode0
Symbolic Models for Infinite Networks of Control Systems: A Compositional Approach—0
Progressive Neural Image Compression with Nested Quantization and Latent Ordering—0
Low Bit-Rate Wideband Speech Coding: A Deep Generative Model based Approach—0
Compressed Object DetectionCode0
Show:102550
← PrevPage 73 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