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 2251–2275 of 4925 papers

TitleStatusHype
MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network QuantizationCode1
Analyzing Compression Techniques for Computer Vision—0
GSB: Group Superposition Binarization for Vision Transformer with Limited Training SamplesCode0
Quantization in Spiking Neural NetworksCode0
Accelerator-Aware Training for Transducer-Based Speech Recognition—0
PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel TransformerCode1
Speaker Diaphragm Excursion Prediction: deep attention and online adaptation—0
Patch-wise Mixed-Precision Quantization of Vision Transformer—0
Post-training Model Quantization Using GANs for Synthetic Data GenerationCode0
Mobile Image Restoration via Prior Quantization—0
Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution NetworksCode1
Multiscale Augmented Normalizing Flows for Image Compression—0
Spiking Neural Networks in the Alexiewicz Topology: A New Perspective on Analysis and Error BoundsCode0
CrAFT: Compression-Aware Fine-Tuning for Efficient Visual Task Adaptation—0
Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation—0
A multimodal dynamical variational autoencoder for audiovisual speech representation learningCode0
Vertical Federated Learning over Cloud-RAN: Convergence Analysis and System Optimization—0
Emulation Learning for Neuromimetic Systems—0
AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture SynthesisCode1
Hybrid model for Single-Stage Multi-Person Pose Estimation—0
ICQ: A Quantization Scheme for Best-Arm Identification Over Bit-Constrained Channels—0
Guaranteed Quantization Error Computation for Neural Network Model Compression—0
Killing Two Birds with One Stone: Quantization Achieves Privacy in Distributed Learning—0
Membrane Potential Distribution Adjustment and Parametric Surrogate Gradient in Spiking Neural Networks—0
The Bjøntegaard Bible -- Why your Way of Comparing Video Codecs May Be WrongCode1
Show:102550
← PrevPage 91 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