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 4651–4700 of 4925 papers

TitleStatusHype
The Neural Network Pushdown Automaton: Model, Stack and Learning SimulationsCode0
Weightless: Lossy Weight Encoding For Deep Neural Network CompressionCode0
ADaPTION: Toolbox and Benchmark for Training Convolutional Neural Networks with Reduced Numerical Precision Weights and Activation—0
Quantized Memory-Augmented Neural Networks—0
Unbounded cache model for online language modeling with open vocabularyCode0
Distribution-Preserving k-Anonymity—0
Compressing Word Embeddings via Deep Compositional Code LearningCode0
Attacking Binarized Neural Networks—0
SUT System Description for Anti-Spoofing 2017 Challenge—0
Efficient Inferencing of Compressed Deep Neural Networks—0
Towards Effective Low-bitwidth Convolutional Neural NetworksCode0
Deep Hashing with Triplet Quantization Loss—0
Quantization goes Polynomial—0
Deep Learning as a Mixed Convex-Combinatorial Optimization ProblemCode0
Using the quantization error from Self-Organized Map (SOM) output for detecting critical variability in large bodies of image time series in less than a minute—0
High Five: Improving Gesture Recognition by Embracing Uncertainty—0
End-to-End Optimized Speech Coding with Deep Neural Networks—0
A Survey of Model Compression and Acceleration for Deep Neural Networks—0
Low Precision RNNs: Quantizing RNNs Without Losing Accuracy—0
Vector Quantization using the Improved Differential Evolution Algorithm for Image Compression—0
TensorQuant - A Simulation Toolbox for Deep Neural Network QuantizationCode0
STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognition—0
Quantized Minimum Error Entropy Criterion—0
Compressive Quantization for Fast Object Instance Search in Videos—0
3D Surface Detail Enhancement From a Single Normal Map—0
AnnArbor: Approximate Nearest Neighbors Using Arborescence Coding—0
The model of an anomaly detector for HiLumi LHC magnets based on Recurrent Neural Networks and adaptive quantizationCode0
Compressing Low Precision Deep Neural Networks Using Sparsity-Induced Regularization in Ternary Networks—0
E^2BoWs: An End-to-End Bag-of-Words Model via Deep Convolutional Neural Network—0
Simulated Annealing for JPEG Quantization—0
Towards Compact and Fast Neural Machine Translation Using a Combined Method—0
Joint Maximum Purity Forest with Application to Image Super-ResolutionCode0
Performance Guaranteed Network Acceleration via High-Order Residual Quantization—0
Neural Networks Compression for Language Modeling—0
Deep Neural Network Capacity—0
SUBIC: A supervised, structured binary code for image search—0
Learning Accurate Low-Bit Deep Neural Networks with Stochastic QuantizationCode0
Monocular Depth Estimation with Hierarchical Fusion of Dilated CNNs and Soft-Weighted-Sum InferenceCode0
ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning—0
Learning Bag-of-Features Pooling for Deep Convolutional Neural NetworksCode0
Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM—0
Model compression as constrained optimization, with application to neural nets. Part II: quantization—0
A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising—0
Model compression as constrained optimization, with application to neural nets. Part I: general framework—0
Learning Deep Binary Descriptor With Multi-Quantization—0
Deep Visual-Semantic Quantization for Efficient Image Retrieval—0
Weighted-Entropy-Based Quantization for Deep Neural Networks—0
Product Split Trees—0
Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks—0
Representation Learning using Event-based STDP—0
Show:102550
← PrevPage 94 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