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 301–350 of 4925 papers

TitleStatusHype
GAN Slimming: All-in-One GAN Compression by A Unified Optimization FrameworkCode1
Fully Quantized Image Super-Resolution NetworksCode1
CrAM: A Compression-Aware MinimizerCode1
Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient AdaptationCode1
Accordion: Adaptive Gradient Communication via Critical Learning Regime IdentificationCode1
CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image TranslationCode1
Structured Multi-Track Accompaniment Arrangement via Style Prior ModellingCode1
ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of MultipliersCode1
CPLLM: Clinical Prediction with Large Language ModelsCode1
Generative De-Quantization for Neural Speech Codec via Latent DiffusionCode1
Heatmap Regression via Randomized RoundingCode1
Fractional Skipping: Towards Finer-Grained Dynamic CNN InferenceCode1
Convolutional Autoencoder-Based Phase Shift Feedback Compression for Intelligent Reflecting Surface-Assisted Wireless SystemsCode1
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN TrainingCode1
FQ-ViT: Post-Training Quantization for Fully Quantized Vision TransformerCode1
ConveRT: Efficient and Accurate Conversational Representations from TransformersCode1
FracBits: Mixed Precision Quantization via Fractional Bit-WidthsCode1
FrameQuant: Flexible Low-Bit Quantization for TransformersCode1
Continual Learning via Bit-Level Information PreservingCode1
Context-aware Communication for Multi-agent Reinforcement LearningCode1
Continuous Visual Autoregressive Generation via Score MaximizationCode1
FP8 Quantization: The Power of the ExponentCode1
FretNet: Continuous-Valued Pitch Contour Streaming for Polyphonic Guitar Tablature TranscriptionCode1
FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning SimulationsCode1
Confounding Tradeoffs for Neural Network QuantizationCode1
FOX-NAS: Fast, On-device and Explainable Neural Architecture SearchCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
Conditional Coding and Variable Bitrate for Practical Learned Video CodingCode1
FP4 All the Way: Fully Quantized Training of LLMsCode1
COMQ: A Backpropagation-Free Algorithm for Post-Training QuantizationCode1
Compression with Bayesian Implicit Neural RepresentationsCode1
1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bitCode1
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-ResolutionCode1
From Analog to Digital: Multi-Order Digital Joint Coding-Modulation for Semantic CommunicationCode1
Compressing LLMs: The Truth is Rarely Pure and Never SimpleCode1
Fine-grained Data Distribution Alignment for Post-Training QuantizationCode1
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural NetworksCode1
FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix ApproximationCode1
Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement LearningCode1
Fine-tuning Quantized Neural Networks with Zeroth-order OptimizationCode1
Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint ReductionCode1
Compress Any Segment Anything Model (SAM)Code1
Few shot font generation via transferring similarity guided global style and quantization local styleCode1
Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal HashingCode1
2DQuant: Low-bit Post-Training Quantization for Image Super-ResolutionCode1
FFNeRV: Flow-Guided Frame-Wise Neural Representations for VideosCode1
Finite Scalar Quantization: VQ-VAE Made SimpleCode1
ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and QuantizationCode1
Compact representations of convolutional neural networks via weight pruning and quantizationCode1
Feature Quantization Improves GAN TrainingCode1
Show:102550
← PrevPage 7 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