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 2451–2500 of 4925 papers

TitleStatusHype
MAUVE Scores for Generative Models: Theory and PracticeCode2
Quantizing Heavy-tailed Data in Statistical Estimation: (Near) Minimax Rates, Covariate Quantization, and Uniform Recovery—0
NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise ModelingCode0
Biologically Plausible Learning on Neuromorphic Hardware Architectures—0
FlatENN: Train Flat for Enhanced Fault Tolerance of Quantized Deep Neural Networks—0
Publishing Efficient On-device Models Increases Adversarial Vulnerability—0
Hyperspherical Quantization: Toward Smaller and More Accurate Models—0
Hyperspherical Loss-Aware Ternary Quantization—0
Development of a Thermodynamics of Human Cognition and Human Culture—0
FFNeRV: Flow-Guided Frame-Wise Neural Representations for VideosCode1
Cross-Dataset Propensity Estimation for Debiasing Recommender Systems—0
Training Integer-Only Deep Recurrent Neural Networks—0
EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models—0
Automatic Network Adaptation for Ultra-Low Uniform-Precision Quantization—0
Towards Neural Variational Monte Carlo That Scales Linearly with System Size—0
QuantArt: Quantizing Image Style Transfer Towards High Visual FidelityCode1
Redistribution of Weights and Activations for AdderNet Quantization—0
CSMPQ:Class Separability Based Mixed-Precision Quantization—0
Model Predictive Control for Neuromimetic Quantized Systems—0
The case for 4-bit precision: k-bit Inference Scaling LawsCode4
Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised LearningCode1
Atrous Space Bender U-Net (ASBU-Net/LogiNet)—0
RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision TransformersCode1
Joint SPX-VIX calibration with Gaussian polynomial volatility models: deep pricing with quantization hints—0
NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution—0
Towards Hardware-Specific Automatic Compression of Neural Networks—0
Huber-energy measure quantization—0
Efficient Speech Representation Learning with Low-Bit Quantization—0
PD-Quant: Post-Training Quantization based on Prediction Difference MetricCode1
Image Compression with Product Quantized Masked Image Modeling—0
Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction—0
Error-aware Quantization through Noise Tempering—0
ResFed: Communication Efficient Federated Learning by Transmitting Deep Compressed Residuals—0
QVIP: An ILP-based Formal Verification Approach for Quantized Neural NetworksCode0
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference—0
Genie: Show Me the Data for QuantizationCode0
TinyKG: Memory-Efficient Training Framework for Knowledge Graph Neural Recommender Systems—0
QEBVerif: Quantization Error Bound Verification of Neural NetworksCode0
CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification—0
FretNet: Continuous-Valued Pitch Contour Streaming for Polyphonic Guitar Tablature TranscriptionCode1
Quantized Wasserstein Procrustes Alignment of Word Embedding Spaces—0
QFT: Post-training quantization via fast joint finetuning of all degrees of freedom—0
Make RepVGG Greater Again: A Quantization-aware ApproachCode0
Device Interoperability for Learned Image Compression with Weights and Activations Quantization—0
Shining light on data: Geometric data analysis through quantum dynamics—0
Robust Task-Specific Beamforming with Low-Resolution ADCs for Power-Efficient Hybrid MIMO Receivers—0
Quadapter: Adapter for GPT-2 Quantization—0
Distributed Computation of Exact Average Degree and Network Size in Finite Number of Steps under Quantized Communication—0
Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural NetworksCode0
Compressing Volumetric Radiance Fields to 1 MBCode2
Show:102550
← PrevPage 50 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