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 3151–3200 of 4925 papers

TitleStatusHype
Neural Compression-Based Feature Learning for Video Restoration—0
Convert, compress, correct: Three steps toward communication-efficient DNN trainingCode0
Covariance Recovery for One-Bit Sampled Data With Time-Varying Sampling Thresholds-Part I: Stationary Signals—0
Implicit Feature Decoupling with Depthwise QuantizationCode0
Learning Spatio-Temporal Downsampling for Effective Video Upscaling—0
Privacy-Preserving Speech Representation Learning using Vector Quantization—0
TAS: Ternarized Neural Architecture Search for Resource-Constrained Edge DevicesCode0
A Mixed Quantization Network for Computationally Efficient Mobile Inverse Tone MappingCode0
Video Coding for Machines with Feature-Based Rate-Distortion Optimization—0
Wireless Quantized Federated Learning: A Joint Computation and Communication Design—0
An Empirical Study of Low Precision Quantization for TinyML—0
Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks—0
Correlated quantization for distributed mean estimation and optimization—0
Neural Network Training on In-memory-computing Hardware with Radix-4 Gradients—0
Givens Coordinate Descent Methods for Rotation Matrix Learning in Trainable Embedding Indexes—0
YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers—0
Practical cognitive speech compression—0
A comparative study of several ADPCM schemes with linear and nonlinear prediction—0
Forward Link Analysis for Full-Duplex Cellular Networks with Low Resolution ADC/DAC—0
Non-linear predictive vector quantization of speech—0
Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inference—0
Transformations in Learned Image Compression from a Modulation Perspective—0
Improving the Energy Efficiency and Robustness of tinyML Computer Vision using Log-Gradient Input Images—0
On the relevance of language in speaker recognition—0
Joint Optimization of Rate, Distortion, and Decoding Energy for HEVC Intraframe Coding—0
ARM 4-BIT PQ: SIMD-based Acceleration for Approximate Nearest Neighbor Search on ARM—0
Region-of-Interest Based Neural Video Compression—0
Engineering the Neural Automatic Passenger Counter—0
Comprehensive Analysis of the Object Detection Pipeline on UAVsCode0
LISA: Learning Interpretable Skill Abstractions from LanguageCode0
High Dimensional Statistical Estimation under Uniformly Dithered One-bit Quantization—0
A blob method for inhomogeneous diffusion with applications to multi-agent control and sampling—0
ANTLER: Bayesian Nonlinear Tensor Learning and Modeler for Unstructured, Varying-Size Point Cloud Data—0
The effect of fatigue on the performance of online writer recognition—0
A comparative study of several parameterizations for speaker recognition—0
Standard Deviation-Based Quantization for Deep Neural Networks—0
Minimax Optimal Quantization of Linear Models: Information-Theoretic Limits and Efficient Algorithms—0
Energy-Efficient Respiratory Anomaly Detection in Premature Newborn Infants—0
Diversity in deep generative models and generative AICode0
Amenable Sparse Network Investigator—0
VCVTS: Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion—0
LG-LSQ: Learned Gradient Linear Symmetric Quantization—0
Quantisation-aware Precoding for MU-MIMO with Limited-capacity Fronthaul—0
Explaining Reject Options of Learning Vector Quantization ClassifiersCode0
Efficient Cross-Modal Retrieval via Deep Binary Hashing and QuantizationCode0
Post-Training Quantization for Cross-Platform Learned Image Compression—0
MuZero with Self-competition for Rate Control in VP9 Video Compression—0
Vau da muntanialas: Energy-efficient multi-die scalable acceleration of RNN inference—0
Quantization in Layer's Input is Matter—0
On One-Bit Quantization—0
Show:102550
← PrevPage 64 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