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 4551–4600 of 4925 papers

TitleStatusHype
Quantizing Convolutional Neural Networks for Low-Power High-Throughput Inference Engines—0
Mad Max: Affine Spline Insights into Deep Learning—0
Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks—0
Towards Accurate and High-Speed Spiking Neuromorphic Systems with Data Quantization-Aware Deep Networks—0
Discrete Factorization Machines for Fast Feature-based RecommendationCode0
Quantization Mimic: Towards Very Tiny CNN for Object Detection—0
Noise Invariant Frame Selection: A Simple Method to Address the Background Noise Problem for Text-independent Speaker VerificationCode0
UNIQ: Uniform Noise Injection for Non-Uniform Quantization of Neural Networks—0
Accurate Sine-Wave Amplitude Measurements Using Nonlinearly Quantized Data—0
Information and Statistical Efficiency When Quantizing Noisy DC Values—0
Quantized Compressive K-Means—0
Dynamic Signal Measurements Based on Quantized Data—0
Robust Anomaly-Based Ship Proposals Detection from Pan-sharpened High-Resolution Satellite Image—0
Deep Convolutional AutoEncoder-based Lossy Image CompressionCode0
Single-User mmWave Massive MIMO: SVD-based ADC Bit Allocation and Combiner Design—0
MQGrad: Reinforcement Learning of Gradient Quantization in Parameter Server—0
On the Impact of Fixed Point Hardware for Optical Fiber Nonlinearity Compensation Algorithms—0
Value-aware Quantization for Training and Inference of Neural Networks—0
A Rigorous Analysis of Least Squares Sine Fitting Using Quantized Data: the Random Phase Case—0
Efficient Channel Estimator with Angle-Division Multiple Access—0
Pieces of Eight: 8-bit Neural Machine Translation—0
Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and MemoryCode0
Discriminative Cross-View Binary Representation Learning—0
A Compressed Sensing Approach for Distribution Matching—0
Detection of Structural Change in Geographic Regions of Interest by Self Organized Mapping: Las Vegas City and Lake Mead across the YearsCode0
Bernoulli Embeddings for Graphs—0
A Quantization-Friendly Separable Convolution for MobileNetsCode0
Gradient Descent Quantizes ReLU Network Features—0
Incremental Color Quantization for Color-Vision-Deficient Observers Using Mobile Gaming Data—0
Unsupervised Semantic Deep Hashing—0
Word2Bits - Quantized Word VectorsCode0
Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial ExamplesCode0
Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation—0
High-Accuracy Low-Precision TrainingCode0
ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range ContentCode0
Deep Neural Network Compression with Single and Multiple Level QuantizationCode0
Hyperdrive: A Multi-Chip Systolically Scalable Binary-Weight CNN Inference Engine—0
Learning-Based Dequantization For Image Restoration Against Extremely Poor Illumination—0
XNORBIN: A 95 TOp/s/W Hardware Accelerator for Binary Convolutional Neural Networks—0
Scalar Quantization as Sparse Least Square Optimization—0
L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks—0
Loss-aware Weight Quantization of Deep NetworksCode0
Autoencoder based image compression: can the learning be quantization independent?—0
3LC: Lightweight and Effective Traffic Compression for Distributed Machine Learning—0
Low complexity convolutional neural network for vessel segmentation in portable retinal diagnostic devices—0
Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation—0
Simultaneous Compression and Quantization: A Joint Approach for Efficient Unsupervised Hashing—0
Model compression via distillation and quantizationCode0
RNN-SM: Fast Steganalysis of VoIP Streams Using Recurrent Neural NetworkCode0
Compressive Sensing Using Iterative Hard Thresholding with Low Precision Data Representation: Theory and Applications—0
Show:102550
← PrevPage 92 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