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 2501–2550 of 4925 papers

TitleStatusHype
UDE: A Unified Driving Engine for Human Motion GenerationCode1
NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision TransformersCode1
Entropy-Driven Mixed-Precision Quantization for Deep Network Design—0
Accelerating Antimicrobial Peptide Discovery with Latent StructureCode1
Post-training Quantization on Diffusion ModelsCode1
Quantized control of non-Lipschitz nonlinear systems: a novel control framework with prescribed transient performance and lower design complexity—0
Post-Processing Temporal Action DetectionCode1
Class-based Quantization for Neural Networks—0
Homology-constrained vector quantization entropy regularizerCode0
A 65nm 8b-Activation 8b-Weight SRAM-Based Charge-Domain Computing-in-Memory Macro Using A Fully-Parallel Analog Adder Network and A Single-ADC Interface—0
Vector Quantization Methods for Access Point Placement in Cell-Free Massive MIMO Systems—0
Join the High Accuracy Club on ImageNet with A Binary Neural Network TicketCode1
RIS-Assisted Self-Interference Mitigation for In-Band Full-Duplex Transceivers—0
High-Perceptual Quality JPEG Decoding via Posterior Sampling—0
Learning Low-Rank Representations for Model Compression—0
Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer EncodersCode0
A Closed-loop Sleep Modulation System with FPGA-Accelerated Deep Learning—0
Deep Learning-Aided Perturbation Model-Based Fiber Nonlinearity Compensation—0
Multiuser-MIMO Systems Using Comparator Network-Aided Receivers With 1-Bit Quantization—0
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language ModelsCode6
Brain Inspired Cortical Coding Method for Fast Clustering and Codebook Generation—0
Zero-Shot Dynamic Quantization for Transformer InferenceCode0
Dynamic Predictive Sampling Analog to Digital Converter for Sparse Signal Sensing—0
Fully Digital Second-order Level-crossing Sampling ADC for Data Saving in Sensing Sparse Signals—0
CPT-V: A Contrastive Approach to Post-Training Quantization of Vision Transformers—0
HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers—0
Optimal Privacy Preserving for Federated Learning in Mobile Edge Computing—0
Edge-MultiAI: Multi-Tenancy of Latency-Sensitive Deep Learning Applications on Edge—0
FullPack: Full Vector Utilization for Sub-Byte Quantized Inference on General Purpose CPUs—0
Long-Range Zero-Shot Generative Deep Network Quantization—0
Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware TrainingCode0
Efficiently Scaling Transformer Inference—0
Quantization-Based Optimization: Alternative Stochastic Approximation of Global Optimization—0
Optimal Discrete Beamforming of RIS-Aided Wireless Communications: An Inner Product Maximization ApproachCode1
Learning Semantic Textual Similarity via Topic-informed Discrete Latent VariablesCode0
Rate-Distortion Optimized Post-Training Quantization for Learned Image Compression—0
A Robust and Low Complexity Deep Learning Model for Remote Sensing Image Classification—0
Quantization Adaptor for Bit-Level Deep Learning-Based Massive MIMO CSI FeedbackCode1
Emergent Quantized Communication—0
Quantized Precoding and RIS-Assisted Modulation for Integrated Sensing and Communications Systems—0
Quantized Compressed Sensing with Score-based Generative ModelsCode1
CNN-based first quantization estimation of double compressed JPEG imagesCode1
IM-Loss: Information Maximization Loss for Spiking Neural Networks—0
Model Compression for DNN-based Speaker Verification Using Weight Quantization—0
Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation—0
Efficient Document Retrieval by End-to-End Refining and Quantizing BERT Embedding with Contrastive Product QuantizationCode0
QuaLA-MiniLM: a Quantized Length Adaptive MiniLM—0
Adaptive Compression for Communication-Efficient Distributed Training—0
Block-Wise Dynamic-Precision Neural Network Training Acceleration via Online Quantization Sensitivity Analytics—0
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained TransformersCode7
Show:102550
← PrevPage 51 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