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 751–800 of 4925 papers

TitleStatusHype
Data-Free Quantization Through Weight Equalization and Bias CorrectionCode1
MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank CompensatorsCode1
A Little Bit More: Bitplane-Wise Bit-Depth RecoveryCode1
Mesa: A Memory-saving Training Framework for TransformersCode1
CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image TranslationCode1
FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning SimulationsCode1
D^2-DPM: Dual Denoising for Quantized Diffusion Probabilistic ModelsCode1
MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable QuantizationCode1
FOX-NAS: Fast, On-device and Explainable Neural Architecture SearchCode1
CrAM: A Compression-Aware MinimizerCode1
MELTing point: Mobile Evaluation of Language TransformersCode1
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and QuantizationCode1
CPLLM: Clinical Prediction with Large Language ModelsCode1
Automatic Perturbation Analysis for Scalable Certified Robustness and BeyondCode1
DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution NetworksCode1
Channel Estimation for Quantized Systems based on Conditionally Gaussian Latent ModelsCode1
AlignQ: Alignment Quantization With ADMM-Based Correlation PreservationCode1
Convolutional Autoencoder-Based Phase Shift Feedback Compression for Intelligent Reflecting Surface-Assisted Wireless SystemsCode1
Matrix Compression via Randomized Low Rank and Low Precision FactorizationCode1
Enhancing Text-based Knowledge Graph Completion with Zero-Shot Large Language Models: A Focus on Semantic EnhancementCode1
Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and CompressionCode1
Data-Free Network Quantization With Adversarial Knowledge DistillationCode1
Continuous Visual Autoregressive Generation via Score MaximizationCode1
Quantized Compressed Sensing with Score-based Generative ModelsCode1
ConveRT: Efficient and Accurate Conversational Representations from TransformersCode1
Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAECode1
APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision TransformersCode1
Raw Image Reconstruction with Learned Compact MetadataCode1
Matching-oriented Embedding Quantization For Ad-hoc RetrievalCode1
Generative Adversarial Super-Resolution at the Edge with Knowledge DistillationCode1
Generative Low-bitwidth Data Free QuantizationCode1
Genetic Quantization-Aware Approximation for Non-Linear Operations in TransformersCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
Confounding Tradeoffs for Neural Network QuantizationCode1
Making DensePose fast and lightCode1
Context-aware Communication for Multi-agent Reinforcement LearningCode1
MagR: Weight Magnitude Reduction for Enhancing Post-Training QuantizationCode1
APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor CoresCode1
Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech TranslationCode1
Gradient-based Automatic Mixed Precision Quantization for Neural Networks On-ChipCode1
COMQ: A Backpropagation-Free Algorithm for Post-Training QuantizationCode1
Algorithm-hardware Co-design for Deformable ConvolutionCode1
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-ResolutionCode1
RepCodec: A Speech Representation Codec for Speech TokenizationCode1
LSQ+: Improving low-bit quantization through learnable offsets and better initializationCode1
Conditional Coding and Variable Bitrate for Practical Learned Video CodingCode1
Guided Hybrid Quantization for Object detection in Multimodal Remote Sensing Imagery via One-to-one Self-teachingCode1
Resolution Switchable Networks for Runtime Efficient Image RecognitionCode1
M^3GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and GenerationCode1
Machine Unlearning of Federated ClustersCode1
Show:102550
← PrevPage 16 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