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 4101–4125 of 4925 papers

TitleStatusHype
AddNet: Deep Neural Networks Using FPGA-Optimized Multipliers—0
CoopNet: Cooperative Convolutional Neural Network for Low-Power MCUsCode0
vqSGD: Vector Quantized Stochastic Gradient Descent—0
Efficient Hardware Implementation of Incremental Learning and Inference on Chip—0
Transductive Zero-Shot Hashing for Multilabel Image RetrievalCode0
Loss Aware Post-training QuantizationCode0
Data Efficient Stagewise Knowledge DistillationCode0
One-Bit Sigma-Delta modulation on the circle—0
The Canonical Distortion Measure for Vector Quantization and Function Approximation—0
DupNet: Towards Very Tiny Quantized CNN with Improved Accuracy for Face Detection—0
What Do Compressed Deep Neural Networks Forget?Code0
Quantization-based Bermudan option pricing in the FX world—0
Hyper-Sphere Quantization: Communication-Efficient SGD for Federated LearningCode0
Norm-Explicit Quantization: Improving Vector Quantization for Maximum Inner Product SearchCode0
Iteratively Training Look-Up Tables for Network Quantization—0
Multiple yield curve modelling with CBI processes—0
A Programmable Approach to Neural Network CompressionCode0
Post-Training 4-bit Quantization on Embedding Tables—0
Ternary MobileNets via Per-Layer Hybrid Filter Banks—0
Comprehensive SNN Compression Using ADMM Optimization and Activity RegularizationCode0
Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers—0
LFZip: Lossy compression of multivariate floating-point time series data via improved predictionCode0
Memory Requirement Reduction of Deep Neural Networks Using Low-bit Quantization of Parameters—0
MulCode: A Multiplicative Multi-way Model for Compressing Neural Language Model—0
On Distributed Quantization for Classification—0
Show:102550
← PrevPage 165 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