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 901–950 of 4925 papers

TitleStatusHype
Neural Network Activation Quantization with Bitwise Information BottlenecksCode0
Neural Architecture Codesign for Fast Physics ApplicationsCode0
Neural Network Assisted Lifting Steps For Improved Fully Scalable Lossy Image Compression in JPEG 2000Code0
NestQuant: Post-Training Integer-Nesting Quantization for On-Device DNNCode0
Nearly Lossless Adaptive Bit SwitchingCode0
NeUQI: Near-Optimal Uniform Quantization Parameter InitializationCode0
Aggregated Learning: A Vector-Quantization Approach to Learning Neural Network ClassifiersCode0
Multi-Excitation Projective Simulation with a Many-Body Physics Inspired Inductive BiasCode0
4bit-Quantization in Vector-Embedding for RAGCode0
Multi-Class Uncertainty Calibration via Mutual Information Maximization-based BinningCode0
Natural Quantization of Neural NetworksCode0
Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer GateCode0
Monocular Depth Estimation with Hierarchical Fusion of Dilated CNNs and Soft-Weighted-Sum InferenceCode0
MorpheusNet: Resource efficient sleep stage classifier for embedded on-line systemsCode0
Modulated Diffusion: Accelerating Generative Modeling with Modulated QuantizationCode0
Modular Quantization-Aware Training for 6D Object Pose EstimationCode0
MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete DiffusionCode0
Model-Aware Deep Architectures for One-Bit Compressive Variational AutoencodingCode0
Model Compression Techniques in Biometrics Applications: A SurveyCode0
Model compression via distillation and quantizationCode0
Mixed-TD: Efficient Neural Network Accelerator with Layer-Specific Tensor DecompositionCode0
Mixed-Precision Quantization and Parallel Implementation of Multispectral Riemannian Classification for Brain--Machine InterfacesCode0
Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation RegularizationCode0
Computational data analysis for first quantization estimation on JPEG double compressed imagesCode0
Mixed Non-linear Quantization for Vision TransformersCode0
Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic ProgrammingCode0
MINT: Multiplier-less INTeger Quantization for Energy Efficient Spiking Neural NetworksCode0
Minimal Random Code Learning: Getting Bits Back from Compressed Model ParametersCode0
Mirror Descent View for Neural Network QuantizationCode0
Accurate and Efficient Fine-Tuning of Quantized Large Language Models Through Optimal BalanceCode0
MetaAug: Meta-Data Augmentation for Post-Training QuantizationCode0
Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On MicrocontrollersCode0
Merge-Friendly Post-Training Quantization for Multi-Target Domain AdaptationCode0
McQueen : Mixed Precision Quantization of Early Exit NetworksCode0
Megapixel Image Generation with Step-Unrolled Denoising AutoencodersCode0
Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMsCode0
A Simple Low-bit Quantization Framework for Video Snapshot Compressive ImagingCode0
Model Compression with Adversarial Robustness: A Unified Optimization FrameworkCode0
Make RepVGG Greater Again: A Quantization-aware ApproachCode0
Maestro: Uncovering Low-Rank Structures via Trainable DecompositionCode0
Minimize Quantization Output Error with Bias CompensationCode0
Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and EfficiencyCode0
LVPNet: A Latent-variable-based Prediction-driven End-to-end Framework for Lossless Compression of Medical ImagesCode0
Compressing Word Embeddings via Deep Compositional Code LearningCode0
LSQ++: Lower running time and higher recall in multi-codebook quantizationCode0
LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model CompressionCode0
Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-AirCode0
Compressing Vision Transformers for Low-Resource Visual LearningCode0
LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural NetworksCode0
LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling MatricesCode0
Show:102550
← PrevPage 19 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