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 4176–4200 of 4925 papers

TitleStatusHype
Learning Compact Embedding Layers via Differentiable Product Quantization—0
Compression without Quantization—0
Learning to Seek: Autonomous Source Seeking with Deep Reinforcement Learning Onboard a Nano Drone MicrocontrollerCode0
CAT: Compression-Aware Training for bandwidth reductionCode0
Low Rank Training of Deep Neural Networks for Emerging Memory Technology—0
Towards Effective 2-bit Quantization: Pareto-optimal Bit Allocation for Deep CNNs Compression—0
OPTIMAL BINARY QUANTIZATION FOR DEEP NEURAL NETWORKS—0
On the Pareto Efficiency of Quantized CNN—0
Online Learned Continual Compression with Stacked Quantization Modules—0
Monte Carlo Deep Neural Network Arithmetic—0
Network Pruning for Low-Rank Binary Index—0
GQ-Net: Training Quantization-Friendly Deep Networks—0
Forward and Backward Information Retention for Accurate Binary Neural NetworksCode0
Autoencoder-Based Error Correction Coding for One-Bit Quantization—0
A System-Level Solution for Low-Power Object Detection—0
Gridless Angular Domain Channel Estimation for mmWave Massive MIMO System With One-Bit Quantization Via Approximate Message Passing—0
Structured Binary Neural Networks for Image Recognition—0
HAWKEYE: Adversarial Example Detector for Deep Neural Networks—0
How to design a derivatives market?—0
Performance Analysis of Massive MIMO Multi-Way Relay Networks with Low-Resolution ADCs—0
How Does Batch Normalization Help Binary Training?—0
Fast Large-Scale Discrete Optimization Based on Principal Coordinate Descent—0
An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platforms—0
DASNet: Dynamic Activation Sparsity for Neural Network Efficiency Improvement—0
Neural Machine Translation with 4-Bit Precision and Beyond—0
Show:102550
← PrevPage 168 of 197Next →
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