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 3051–3100 of 4925 papers

TitleStatusHype
Asymmetric Learned Image Compression with Multi-Scale Residual Block, Importance Map, and Post-Quantization Filtering—0
Self-Supervised Consistent Quantization for Fully Unsupervised Image Retrieval—0
Low-Precision Stochastic Gradient Langevin DynamicsCode0
Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge NodesCode0
Towards Efficient Active Learning of PDFACode0
tinySNN: Towards Memory- and Energy-Efficient Spiking Neural Networks—0
Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization—0
Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data—0
Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networks—0
Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial PruningCode0
Towards Alternative Techniques for Improving Adversarial Robustness: Analysis of Adversarial Training at a Spectrum of PerturbationsCode0
Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks—0
Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware TrainingCode0
Preprocessing Enhanced Image Compression for Machine Vision—0
A Directed-Evolution Method for Sparsification and Compression of Neural Networks with Application to Object Identification and Segmentation and considerations of optimal quantization using small number of bits—0
Convex Quantization Preserves Logconcavity—0
Real-time Hyper-Dimensional Reconfiguration at the Edge using Hardware Accelerators—0
HideNseek: Federated Lottery Ticket via Server-side Pruning and Sign Supermask—0
SDQ: Stochastic Differentiable Quantization with Mixed Precision—0
Memory-Oriented Design-Space Exploration of Edge-AI Hardware for XR Applications—0
Low-complexity acoustic scene classification in DCASE 2022 Challenge—0
Gradient Obfuscation Gives a False Sense of Security in Federated Learning—0
Enhancing Strong PUF Security with Non-monotonic Response Quantization—0
Learning Binarized Graph Representations with Multi-faceted Quantization Reinforcement for Top-K Recommendation—0
Extreme Compression for Pre-trained Transformers Made Simple and Efficient—0
Completion Time Minimization of Fog-RAN-Assisted Federated Learning With Rate-Splitting Transmission—0
Resource Allocation for Compression-aided Federated Learning with High Distortion Rate—0
Long Scale Error Control in Low Light Image and Video Enhancement Using Equivariance—0
On the Role of Spatial Effects in Early Estimates of Disease Infectiousness: A Second Quantization Approach—0
AMED: Automatic Mixed-Precision Quantization for Edge DevicesCode0
Q-LIC: Quantizing Learned Image Compression with Channel Splitting—0
Efficient-Adam: Communication-Efficient Distributed Adam—0
FCN-Pose: A Pruned and Quantized CNN for Robot Pose Estimation for Constrained Devices—0
QUIC-FL: Quick Unbiased Compression for Federated Learning—0
Federated Split BERT for Heterogeneous Text Classification—0
Sparse*BERT: Sparse Models Generalize To New tasks and Domains—0
A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Maps—0
Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models—0
Approximation speed of quantized vs. unquantized ReLU neural networks and beyond—0
Few-bit Quantization of Neural Networks for Nonlinearity Mitigation in a Fiber Transmission Experiment—0
OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization—0
Nonparametric Decentralized Detection and Sparse Sensor Selection via Multi-Sensor Online Kernel Scalar Quantization—0
Approximate Message Passing with Parameter Estimation for Heavily Quantized MeasurementsCode0
QADAM: Quantization-Aware DNN Accelerator Modeling for Pareto-Optimality—0
Energy-efficient Deployment of Deep Learning Applications on Cortex-M based Microcontrollers using Deep Compression—0
Service Delay Minimization for Federated Learning over Mobile Devices—0
Positional Information is All You Need: A Novel Pipeline for Self-Supervised SVDE from Videos—0
A Silicon Photonic Accelerator for Convolutional Neural Networks with Heterogeneous Quantization—0
Towards Robust Low Light Image Enhancement—0
QAPPA: Quantization-Aware Power, Performance, and Area Modeling of DNN Accelerators—0
Show:102550
← PrevPage 62 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