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 351–400 of 4925 papers

TitleStatusHype
Generative De-Quantization for Neural Speech Codec via Latent DiffusionCode1
Geometric Total Variation for Image Vectorization, Zooming and Pixel Art DepixelizingCode1
Generalizable Mixed-Precision Quantization via Attribution Rank PreservationCode1
Enhancing Text-based Knowledge Graph Completion with Zero-Shot Large Language Models: A Focus on Semantic EnhancementCode1
Generalized Product Quantization Network for Semi-supervised Image RetrievalCode1
Convolutional Autoencoder-Based Phase Shift Feedback Compression for Intelligent Reflecting Surface-Assisted Wireless SystemsCode1
Data-Free Network Quantization With Adversarial Knowledge DistillationCode1
Accelerating Antimicrobial Peptide Discovery with Latent StructureCode1
CPLLM: Clinical Prediction with Large Language ModelsCode1
Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAECode1
Hyper-Compression: Model Compression via HyperfunctionCode1
KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range MultilaterationCode1
FretNet: Continuous-Valued Pitch Contour Streaming for Polyphonic Guitar Tablature TranscriptionCode1
Context-aware Communication for Multi-agent Reinforcement LearningCode1
From Analog to Digital: Multi-Order Digital Joint Coding-Modulation for Semantic CommunicationCode1
Fractional Skipping: Towards Finer-Grained Dynamic CNN InferenceCode1
Conditional Coding and Variable Bitrate for Practical Learned Video CodingCode1
FracBits: Mixed Precision Quantization via Fractional Bit-WidthsCode1
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN TrainingCode1
Compression with Bayesian Implicit Neural RepresentationsCode1
FOX-NAS: Fast, On-device and Explainable Neural Architecture SearchCode1
FP4 All the Way: Fully Quantized Training of LLMsCode1
FP8 Quantization: The Power of the ExponentCode1
Compressing LLMs: The Truth is Rarely Pure and Never SimpleCode1
COMQ: A Backpropagation-Free Algorithm for Post-Training QuantizationCode1
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-ResolutionCode1
Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN TrainingCode1
ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network QuantizationCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
Confounding Tradeoffs for Neural Network QuantizationCode1
FrameQuant: Flexible Low-Bit Quantization for TransformersCode1
Adaptive Gradient Quantization for Data-Parallel SGDCode1
FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning SimulationsCode1
FQ-ViT: Post-Training Quantization for Fully Quantized Vision TransformerCode1
Fine-grained Data Distribution Alignment for Post-Training QuantizationCode1
ConveRT: Efficient and Accurate Conversational Representations from TransformersCode1
Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement LearningCode1
APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision TransformersCode1
Fine-tuning Quantized Neural Networks with Zeroth-order OptimizationCode1
ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and QuantizationCode1
Compact representations of convolutional neural networks via weight pruning and quantizationCode1
CrAM: A Compression-Aware MinimizerCode1
APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor CoresCode1
DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution NetworksCode1
Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal HashingCode1
Finite Scalar Quantization: VQ-VAE Made SimpleCode1
Anonymizing Speech: Evaluating and Designing Speaker Anonymization TechniquesCode1
Generative Low-bitwidth Data Free QuantizationCode1
CommVQ: Commutative Vector Quantization for KV Cache CompressionCode1
Adaptive Debanding FilterCode1
Show:102550
← PrevPage 8 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