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 701–750 of 4925 papers

TitleStatusHype
Efficient-VDVAE: Less is moreCode1
Edge AI-Based Vein Detector for Efficient Venipuncture in the Antecubital FossaCode1
A Little Bit More: Bitplane-Wise Bit-Depth RecoveryCode1
Clustering the Sketch: A Novel Approach to Embedding Table CompressionCode1
Dynamic Network Quantization for Efficient Video InferenceCode1
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution NetworksCode1
EasyQuant: Post-training Quantization via Scale OptimizationCode1
EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the EdgeCode1
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial LearningCode1
Lossy Image Compression with Quantized Hierarchical VAEsCode1
Adaptive Data-Free QuantizationCode1
LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model FinetuningCode1
DQS3D: Densely-matched Quantization-aware Semi-supervised 3D DetectionCode1
Machine Unlearning of Federated ClustersCode1
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and QuantizationCode1
Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech TranslationCode1
Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense RetrievalCode1
Automatic Perturbation Analysis for Scalable Certified Robustness and BeyondCode1
DVD-Quant: Data-free Video Diffusion Transformers QuantizationCode1
EFaR 2023: Efficient Face Recognition CompetitionCode1
DNN+NeuroSim V2.0: An End-to-End Benchmarking Framework for Compute-in-Memory Accelerators for On-chip TrainingCode1
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and QuantizationCode1
AlignQ: Alignment Quantization With ADMM-Based Correlation PreservationCode1
MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable QuantizationCode1
Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical StudyCode1
Broken Neural Scaling LawsCode1
DiTAS: Quantizing Diffusion Transformers via Enhanced Activation SmoothingCode1
MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank CompensatorsCode1
Mini-GPTs: Efficient Large Language Models through Contextual PruningCode1
Minimizing FLOPs to Learn Efficient Sparse RepresentationsCode1
Mixed-precision Neural Networks on RISC-V Cores: ISA extensions for Multi-Pumped Soft SIMD OperationsCode1
Diverse Sample Generation: Pushing the Limit of Generative Data-free QuantizationCode1
CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large InputCode1
BAFFLE: A Baseline of Backpropagation-Free Federated LearningCode1
Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense EmbeddingsCode1
Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and CompressionCode1
Distributed Learning Systems with First-order MethodsCode1
Disentanglement via Latent QuantizationCode1
Quantized Compressed Sensing with Score-based Generative ModelsCode1
Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and DistillationCode1
MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion ModelsCode1
MQBench: Towards Reproducible and Deployable Model Quantization BenchmarkCode1
Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution NetworksCode1
MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-DesignCode1
NAPA-VQ: Neighborhood Aware Prototype Augmentation with Vector Quantization for Continual LearningCode1
CE-VAE: Capsule Enhanced Variational AutoEncoder for Underwater Image EnhancementCode1
Catastrophic Failure of LLM Unlearning via QuantizationCode1
CA-SpaceNet: Counterfactual Analysis for 6D Pose Estimation in SpaceCode1
Network Binarization via Contrastive LearningCode1
Effectiveness of self-supervised pre-training for speech recognitionCode1
Show:102550
← PrevPage 15 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