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 4351–4400 of 4925 papers

TitleStatusHype
Cluster Regularized Quantization for Deep Networks Compression—0
Learned Step Size QuantizationCode1
Novel Near-Optimal Scalar Quantizers with Exponential Decay Rate and Global Convergence—0
Low-bit Quantization of Neural Networks for Efficient InferenceCode0
Quantized Frank-Wolfe: Faster Optimization, Lower Communication, and Projection Free—0
AutoQ: Automated Kernel-Wise Neural Network Quantization—0
Model Compression with Adversarial Robustness: A Unified Optimization FrameworkCode0
Binarized Knowledge Graph EmbeddingsCode0
FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary—0
Compression of Recurrent Neural Networks for Efficient Language Modeling—0
Same, Same But Different - Recovering Neural Network Quantization Error Through Weight FactorizationCode0
Supervised Quantization for Similarity Search—0
Collaborative Quantization for Cross-Modal Similarity Search—0
Efficient Hybrid Network Architectures for Extremely Quantized Neural Networks Enabling Intelligence at the Edge—0
Robustness of Generalized Learning Vector Quantization Models against Adversarial AttacksCode0
Deep Triplet QuantizationCode0
Model-Based Detector for SSDs in the Presence of Inter-cell Interference—0
Improving Neural Network Quantization without Retraining using Outlier Channel SplittingCode0
Distributed Learning with Compressed Gradient Differences—0
Subspace Robust Wasserstein Distances—0
QGAN: Quantized Generative Adversarial Networks—0
Nonparametric Inference under B-bits Quantization—0
Learning Space Partitions for Nearest Neighbor SearchCode0
Toward Joint Image Generation and Compression using Generative Adversarial Networks—0
On the Uplink Achievable Rate of Massive MIMO System With Low-Resolution ADC and RF Impairments—0
Hybrid coarse-fine classification for head pose estimationCode0
Foothill: A Quasiconvex Regularization for Edge Computing of Deep Neural Networks—0
Activation Functions for Generalized Learning Vector Quantization - A Performance Comparison—0
Mean Estimation from One-Bit Measurements—0
Quantized Epoch-SGD for Communication-Efficient Distributed Learning—0
GIF2Video: Color Dequantization and Temporal Interpolation of GIF images—0
DSConv: Efficient Convolution OperatorCode0
Dataflow-based Joint Quantization of Weights and Activations for Deep Neural Networks—0
Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-AirCode0
Vector and Line Quantization for Billion-scale Similarity Search on GPUsCode0
ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of MultipliersCode1
Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm—0
Interest Point Detection based on Adaptive Ternary Coding—0
Quantized Guided Pruning for Efficient Hardware Implementations of Convolutional Neural Networks—0
End-to-End Latent Fingerprint Search—0
Precision Highway for Ultra Low-Precision Quantization—0
Artificial neural networks condensation: A strategy to facilitate adaption of machine learning in medical settings by reducing computational burden—0
Quicker ADC : Unlocking the hidden potential of Product Quantization with SIMDCode0
SQuantizer: Simultaneous Learning for Both Sparse and Low-precision Neural Networks—0
Fast Adjustable Threshold For Uniform Neural Network Quantization (Winning solution of LPIRC-II)Code0
Efficient Super Resolution Using Binarized Neural Network—0
Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge—0
Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications—0
Exploring Embedding Methods in Binary Hyperdimensional Computing: A Case Study for Motor-Imagery based Brain-Computer InterfacesCode0
E-RNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs—0
Show:102550
← PrevPage 88 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