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 4801–4850 of 4925 papers

TitleStatusHype
High-Accuracy Low-Precision TrainingCode0
Rethinking floating point for deep learningCode0
The Neural Network Pushdown Automaton: Model, Stack and Learning SimulationsCode0
Approximate spectral clustering density-based similarity for noisy datasetsCode0
CASP: Compression of Large Multimodal Models Based on Attention SparsityCode0
The Power of Negative Zero: Datatype Customization for Quantized Large Language ModelsCode0
Eliminating Quantization Errors in Classification-Based Sound Source LocalizationCode0
Weighted quantization using MMD: From mean field to mean shift via gradient flowsCode0
EAST: Encoding-Aware Sparse Training for Deep Memory Compression of ConvNetsCode0
EAQuant: Enhancing Post-Training Quantization for MoE Models via Expert-Aware OptimizationCode0
Probabilistic Weight Fixing: Large-scale training of neural network weight uncertainties for quantizationCode0
Hierarchical Quantized Representations for Script GenerationCode0
Revealing and Protecting Labels in Distributed TrainingCode0
CoopNet: Cooperative Convolutional Neural Network for Low-Power MCUsCode0
The Quantization Model of Neural ScalingCode0
DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP ProtectionCode0
Hierarchical Encoding of Sequential Data With Compact and Sub-Linear Storage CostCode0
A Comprehensive Evaluation of Quantization Strategies for Large Language ModelsCode0
Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMMCode0
Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and EfficiencyCode0
Hessian Aware Quantization of Spiking Neural NetworksCode0
Convolutional Neural Networks to Enhance Coded SpeechCode0
Revisiting Multi-Codebook QuantizationCode0
Progressive Stochastic Binarization of Deep NetworksCode0
Convert, compress, correct: Three steps toward communication-efficient DNN trainingCode0
Revisiting Saliency Metrics: Farthest-Neighbor Area Under CurveCode0
DSConv: Efficient Convolution OperatorCode0
Cartesian K-MeansCode0
Vector quantization loss analysis in VQGANs: a single-GPU ablation study for image-to-image synthesisCode0
Properties that allow or prohibit transferability of adversarial attacks among quantized networksCode0
ACIQ: Analytical Clipping for Integer Quantization of neural networksCode0
Continuous-variable neural-network quantum states and the quantum rotor modelCode0
DQRM: Deep Quantized Recommendation ModelsCode0
RGCNN: Regularized Graph CNN for Point Cloud SegmentationCode0
Spiking Neural Networks in the Alexiewicz Topology: A New Perspective on Analysis and Error BoundsCode0
HERO: Hessian-Enhanced Robust Optimization for Unifying and Improving Generalization and Quantization PerformanceCode0
RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model AccuracyCode0
ProxQuant: Quantized Neural Networks via Proximal OperatorsCode0
Continual Learning for Generative Retrieval over Dynamic CorporaCode0
BRIDLE: Generalized Self-supervised Learning with QuantizationCode0
Advanced Knowledge Transfer: Refined Feature Distillation for Zero-Shot Quantization in Edge ComputingCode0
Context Unaware Knowledge Distillation for Image RetrievalCode0
HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural NetworksCode0
Spreading vectors for similarity searchCode0
HDRUNet: Single Image HDR Reconstruction with Denoising and DequantizationCode0
Harnessing Large Language Models Locally: Empirical Results and Implications for AI PCCode0
Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devicesCode0
SPT: Fine-Tuning Transformer-based Language Models Efficiently with SparsificationCode0
Ps and Qs: Quantization-aware pruning for efficient low latency neural network inferenceCode0
Hardware Acceleration for Real-Time Wildfire Detection Onboard Drone NetworksCode0
Show:102550
← PrevPage 97 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