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 3751–3800 of 4925 papers

TitleStatusHype
Automatic Gain Control Design for Dynamic Visible Light Communication Systems—0
Automatic low-bit hybrid quantization of neural networks through meta learning—0
Automatic mixed precision for optimizing gained time with constrained loss mean-squared-error based on model partition to sequential sub-graphs—0
Automatic Mixed-Precision Quantization Search of BERT—0
Automatic Network Adaptation for Ultra-Low Uniform-Precision Quantization—0
Automatic Parameter Tying in Neural Networks—0
Automatic Pruning for Quantized Neural Networks—0
Automating Nearest Neighbor Search Configuration with Constrained Optimization—0
AutoMixQ: Self-Adjusting Quantization for High Performance Memory-Efficient Fine-Tuning—0
Automotive Radar Sensing with Sparse Linear Arrays Using One-Bit Hankel Matrix Completion—0
AutoQ: Automated Kernel-Wise Neural Network Quantization—0
AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks—0
Autoregressive High-Order Finite Difference Modulo Imaging: High-Dynamic Range for Computer Vision Applications—0
Auto-regressive Image Synthesis with Integrated Quantization—0
Autoregressive Sign Language Production: A Gloss-Free Approach with Discrete Representations—0
Autoregressive Speech Synthesis without Vector Quantization—0
Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge—0
Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization—0
Avaliação do método dialético na quantização de imagens multiespectrais—0
A Video Coding Method Based on Neural Network for CLIC2024—0
A Vision System for Multi-View Face Recognition—0
A Wave is Worth 100 Words: Investigating Cross-Domain Transferability in Time Series—0
AWEQ: Post-Training Quantization with Activation-Weight Equalization for Large Language Models—0
A White Paper on Neural Network Quantization—0
AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent—0
Background Modelling using Octree Color Quantization—0
Back to Simplicity: How to Train Accurate BNNs from Scratch?—0
Bag of Tricks with Quantized Convolutional Neural Networks for image classification—0
Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks—0
Balance of Number of Embedding and their Dimensions in Vector Quantization—0
Balancing Robustness and Efficiency in Embedded DNNs Through Activation Function Selection—0
BAMSProd: A Step towards Generalizing the Adaptive Optimization Methods to Deep Binary Model—0
Bandlimited signal reconstruction from leaky integrate-and-fire encoding using POCS—0
Bandwidth-efficient Inference for Neural Image Compression—0
Bang for the Buck: Vector Search on Cloud CPUs—0
BasedAI: A decentralized P2P network for Zero Knowledge Large Language Models (ZK-LLMs)—0
BasisConv: A method for compressed representation and learning in CNNs—0
Bayesian-LoRA: LoRA based Parameter Efficient Fine-Tuning using Optimal Quantization levels and Rank Values trough Differentiable Bayesian Gates—0
Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval—0
b-bit Marginal Regression—0
BBQRec: Behavior-Bind Quantization for Multi-Modal Sequential Recommendation—0
BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networks—0
BdSLW401: Transformer-Based Word-Level Bangla Sign Language Recognition Using Relative Quantization Encoding (RQE)—0
BeamVQ: Aligning Space-Time Forecasting Model via Self-training on Physics-aware Metrics—0
BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning—0
BELT:Bootstrapping Electroencephalography-to-Language Decoding and Zero-Shot Sentiment Classification by Natural Language Supervision—0
Benchmarking CFAR and CNN-based Peak Detection Algorithms in ISAC under Hardware Impairments—0
Benchmarking quantized LLaMa-based models on the Brazilian Secondary School Exam—0
Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance—0
Benchmarking the Robustness of Quantized Models—0
Show:102550
← PrevPage 76 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