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 3176–3200 of 4925 papers

TitleStatusHype
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 128 of 197Next →
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