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 2651–2700 of 4925 papers

TitleStatusHype
Patch-wise Mixed-Precision Quantization of Vision Transformer—0
Post-training Model Quantization Using GANs for Synthetic Data GenerationCode0
Mobile Image Restoration via Prior Quantization—0
Multiscale Augmented Normalizing Flows for Image Compression—0
Spiking Neural Networks in the Alexiewicz Topology: A New Perspective on Analysis and Error BoundsCode0
CrAFT: Compression-Aware Fine-Tuning for Efficient Visual Task Adaptation—0
Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation—0
A multimodal dynamical variational autoencoder for audiovisual speech representation learningCode0
Emulation Learning for Neuromimetic Systems—0
Vertical Federated Learning over Cloud-RAN: Convergence Analysis and System Optimization—0
Hybrid model for Single-Stage Multi-Person Pose Estimation—0
ICQ: A Quantization Scheme for Best-Arm Identification Over Bit-Constrained Channels—0
Killing Two Birds with One Stone: Quantization Achieves Privacy in Distributed Learning—0
Guaranteed Quantization Error Computation for Neural Network Model Compression—0
Membrane Potential Distribution Adjustment and Parametric Surrogate Gradient in Spiking Neural Networks—0
Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networks—0
Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations—0
Transformer-based models and hardware acceleration analysis in autonomous driving: A survey—0
Picking Up Quantization Steps for Compressed Image ClassificationCode0
Improving Post-Training Quantization on Object Detection with Task Loss-Guided Lp Metric—0
DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures using Lookup Tables—0
ATHEENA: A Toolflow for Hardware Early-Exit Network Automation—0
Soft Label Coding for End-to-end Sound Source Localization With Ad-hoc Microphone Arrays—0
Convergence rate of Tsallis entropic regularized optimal transport—0
D-SVM over Networked Systems with Non-Ideal Linking Conditions—0
Learning Accurate Performance Predictors for Ultrafast Automated Model CompressionCode0
End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICs—0
Unsupervised Multi-Criteria Adversarial Detection in Deep Image Retrieval—0
Benchmarking the Robustness of Quantized Models—0
Unsupervised Speech Representation Pooling Using Vector QuantizationCode0
AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks—0
FedDiSC: A Computation-efficient Federated Learning Framework for Power Systems Disturbance and Cyber Attack Discrimination—0
Blockwise Compression of Transformer-based Models without Retraining—0
A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation—0
Distributed Optimization for Quadratic Cost Functions over Large-Scale Networks with Quantized Communication and Finite-Time Convergence—0
FP8 versus INT8 for efficient deep learning inference—0
A Joint Model and Data Driven Method for Distributed Estimation—0
oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes—0
SC-VAE: Sparse Coding-based Variational Autoencoder with Learned ISTACode0
Tetra-AML: Automatic Machine Learning via Tensor Networks—0
Low-Dose CT Image Reconstruction using Vector Quantized Convolutional Autoencoder with Perceptual Loss—0
Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis—0
An Evaluation of Memory Optimization Methods for Training Neural Networks—0
LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression—0
Towards Accurate Post-Training Quantization for Vision Transformer—0
Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance—0
The Quantization Model of Neural ScalingCode0
Scaled Quantization for the Vision Transformer—0
Posthoc Interpretation via Quantization—0
Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT SystemsCode0
Show:102550
← PrevPage 54 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