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 3751–3800 of 4925 papers

TitleStatusHype
FATNN: Fast and Accurate Ternary Neural Networks—0
Unsupervised Learning For Sequence-to-sequence Text-to-speech For Low-resource Languages—0
The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020—0
End-to-End Rate-Distortion Optimization for Bi-Directional Learned Video Compression—0
Degree-Quant: Quantization-Aware Training for Graph Neural Networks—0
PROFIT: A Novel Training Method for sub-4-bit MobileNet ModelsCode1
Hardware-Centric AutoML for Mixed-Precision Quantization—0
Knowledge Distillation-aided End-to-End Learning for Linear Precoding in Multiuser MIMO Downlink Systems with Finite-Rate Feedback—0
Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics—0
In-Depth DCT Coefficient Distribution Analysis for First Quantization Estimation—0
Subjective Quality Database and Objective Study of Compressed Point Clouds With 6DoF Head-Mounted Display—0
Fast top-K Cosine Similarity Search through XOR-Friendly Binary Quantization on GPUs—0
TREND: Transferability based Robust ENsemble DesignCode0
A Novel Physics-based Channel Model for Reconfigurable Intelligent Surface-assisted Multi-user Communication Systems—0
Super-relaxation of space-time-quantized ensemble of energy loads to curtail their synchronization after demand response perturbation—0
Cluster-Based Cooperative Digital Over-the-Air Aggregation for Wireless Federated Edge Learning—0
The Rate-Distortion-Accuracy Tradeoff: JPEG Case Study—0
Uplink Achievable Rate of Intelligent Reflecting Surface-Aided Millimeter-Wave Communications with Low-Resolution ADC and Phase Noise—0
Deep Multi-modality Soft-decoding of Very Low Bit-rate Face Videos—0
FTL: A universal framework for training low-bit DNNs via Feature Transfer—0
High-quality Single-model Deep Video Compression with Frame-Conv3D and Multi-frame Differential Modulation—0
ProxyBNN: Learning Binarized Neural Networks via Proxy Matrices—0
Binarized Neural Network for Single Image Super Resolution—0
Task-Aware Quantization Network for JPEG Image Compression—0
Deep Transferring QuantizationCode1
Automatic Gain Control Design for Dynamic Visible Light Communication Systems—0
Geometric Total Variation for Image Vectorization, Zooming and Pixel Art DepixelizingCode1
Communication-Efficient Federated Learning via Optimal Client Sampling—0
Flexible framework for audio reconstructionCode0
On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures—0
WrapNet: Neural Net Inference with Ultra-Low-Resolution Arithmetic—0
End-to-end Learning of Compressible Features—0
Analysis and Optimization for RIS-Aided Multi-Pair Communications Relying on Statistical CSI—0
A Post-coder Feedback Approach to Overcome Training Asymmetry in MIMO-TDD—0
Byzantine-Resilient Secure Federated Learning—0
Differentiable Joint Pruning and Quantization for Hardware Efficiency—0
HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNsCode1
Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization—0
Exploiting vulnerabilities of deep neural networks for privacy protectionCode0
Resolution Switchable Networks for Runtime Efficient Image RecognitionCode1
DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks—0
FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks—0
Training with reduced precision of a support vector machine model for text classification—0
eSampling: Energy Harvesting ADCs—0
Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data AugmentationCode1
Channel-Level Variable Quantization Network for Deep Image CompressionCode1
Compression strategies and space-conscious representations for deep neural networks—0
A General Family of Stochastic Proximal Gradient Methods for Deep Learning—0
Image De-Quantization Using Generative Models as Priors—0
Finding Non-Uniform Quantization Schemes using Multi-Task Gaussian ProcessesCode0
Show:102550
← PrevPage 76 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