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 401–450 of 4925 papers

TitleStatusHype
F8Net: Fixed-Point 8-bit Only Multiplication for Network QuantizationCode1
From Analog to Digital: Multi-Order Digital Joint Coding-Modulation for Semantic CommunicationCode1
Feature-based Federated Transfer Learning: Communication Efficiency, Robustness and PrivacyCode1
GAN Slimming: All-in-One GAN Compression by A Unified Optimization FrameworkCode1
Enhancing Generalization of Universal Adversarial Perturbation through Gradient AggregationCode1
Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained DevicesCode1
Generative Adversarial Super-Resolution at the Edge with Knowledge DistillationCode1
Generative De-Quantization for Neural Speech Codec via Latent DiffusionCode1
End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video CompressionCode1
Genetic Quantization-Aware Approximation for Non-Linear Operations in TransformersCode1
End-to-End Rate-Distortion Optimized 3D Gaussian RepresentationCode1
EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion ModelsCode1
Anonymizing Speech: Evaluating and Designing Speaker Anonymization TechniquesCode1
Gradient-based Automatic Mixed Precision Quantization for Neural Networks On-ChipCode1
EMQ: Evolving Training-free Proxies for Automated Mixed Precision QuantizationCode1
Adaptive Debanding FilterCode1
Embedding in Recommender Systems: A SurveyCode1
AQD: Towards Accurate Fully-Quantized Object DetectionCode1
AQ-GT: a Temporally Aligned and Quantized GRU-Transformer for Co-Speech Gesture SynthesisCode1
Enabling Binary Neural Network Training on the EdgeCode1
HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural NetworksCode1
HAWQV3: Dyadic Neural Network QuantizationCode1
Hierarchical Quantized AutoencodersCode1
Hierarchical Vector Quantization for Unsupervised Action SegmentationCode1
EQ-Net: Elastic Quantization Neural NetworksCode1
Efficient and Robust Quantization-aware Training via Adaptive Coreset SelectionCode1
HiNeRV: Video Compression with Hierarchical Encoding-based Neural RepresentationCode1
Efficient Quantized Sparse Matrix Operations on Tensor CoresCode1
Adaptive Data-Free QuantizationCode1
Arch-Net: Model Distillation for Architecture Agnostic Model DeploymentCode1
Effectiveness of self-supervised pre-training for speech recognitionCode1
EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion ModelsCode1
EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the EdgeCode1
Abstracted Shapes as Tokens -- A Generalizable and Interpretable Model for Time-series ClassificationCode1
Improvements to Target-Based 3D LiDAR to Camera CalibrationCode1
A Refined Analysis of Massive Activations in LLMsCode1
EFaR 2023: Efficient Face Recognition CompetitionCode1
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer ProgrammingCode1
Efficient-VDVAE: Less is moreCode1
ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language GenerationCode1
Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-ResolutionCode1
INT-FP-QSim: Mixed Precision and Formats For Large Language Models and Vision TransformersCode1
DVD-Quant: Data-free Video Diffusion Transformers QuantizationCode1
It's All In the Teacher: Zero-Shot Quantization Brought Closer to the TeacherCode1
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution NetworksCode1
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and QuantizationCode1
Animation from Blur: Multi-modal Blur Decomposition with Motion GuidanceCode1
A Thorough Examination of Decoding Methods in the Era of LLMsCode1
Structured Multi-Track Accompaniment Arrangement via Style Prior ModellingCode1
DQS3D: Densely-matched Quantization-aware Semi-supervised 3D DetectionCode1
Show:102550
← PrevPage 9 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