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 3476–3500 of 4925 papers

TitleStatusHype
Adaptive Dither Voting for Robust Spatial Verification—0
Adaptive Integrate-and-Fire Time Encoding Machine with Quantization—0
Adaptive Joint Optimization for 3D Reconstruction with Differentiable Rendering—0
Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction—0
Adaptive Periodic Averaging: A Practical Approach to Reducing Communication in Distributed Learning—0
Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers—0
Adaptive Proximal Gradient Methods for Structured Neural Networks—0
Adaptive Quantization for Deep Neural Network—0
Adaptive Quantization for Key Generation in Low-Power Wide-Area Networks—0
Adaptive Quantization of Model Updates for Communication-Efficient Federated Learning—0
Adaptive Quantization of Neural Networks—0
Adaptive Quantization Resolution and Power Control for Federated Learning over Cell-free Networks—0
Adaptive quantization with mixed-precision based on low-cost proxy—0
Adaptive Resolution Inference (ARI): Energy-Efficient Machine Learning for Internet of Things—0
Adaptive Resource Allocation for Semantic Communication Networks—0
Adaptive Sample-space & Adaptive Probability coding: a neural-network based approach for compression—0
Adaptive Training of Random Mapping for Data Quantization—0
Adaptive Transmission for Distributed Detection in Energy Harvesting Wireless Sensor Networks—0
Adaptive Wireless Image Semantic Transmission and Over-The-Air Testing—0
Adaptive Wireless Image Semantic Transmission: Design, Simulation, and Prototype Validation—0
AdaptivFloat: A Floating-point based Data Type for Resilient Deep Learning Inference—0
AdaQAT: Adaptive Bit-Width Quantization-Aware Training—0
A Data and Compute Efficient Design for Limited-Resources Deep Learning—0
AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence—0
Additive Quantization for Extreme Vector Compression—0
Show:102550
← PrevPage 140 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