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 3751–3775 of 4925 papers

TitleStatusHype
FATNN: Fast and Accurate Ternary Neural Networks—0
Unsupervised Learning For Sequence-to-sequence Text-to-speech For Low-resource Languages—0
The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020—0
End-to-End Rate-Distortion Optimization for Bi-Directional Learned Video Compression—0
Degree-Quant: Quantization-Aware Training for Graph Neural Networks—0
PROFIT: A Novel Training Method for sub-4-bit MobileNet ModelsCode1
Hardware-Centric AutoML for Mixed-Precision Quantization—0
Knowledge Distillation-aided End-to-End Learning for Linear Precoding in Multiuser MIMO Downlink Systems with Finite-Rate Feedback—0
Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics—0
In-Depth DCT Coefficient Distribution Analysis for First Quantization Estimation—0
Subjective Quality Database and Objective Study of Compressed Point Clouds With 6DoF Head-Mounted Display—0
Fast top-K Cosine Similarity Search through XOR-Friendly Binary Quantization on GPUs—0
TREND: Transferability based Robust ENsemble DesignCode0
A Novel Physics-based Channel Model for Reconfigurable Intelligent Surface-assisted Multi-user Communication Systems—0
Super-relaxation of space-time-quantized ensemble of energy loads to curtail their synchronization after demand response perturbation—0
Cluster-Based Cooperative Digital Over-the-Air Aggregation for Wireless Federated Edge Learning—0
The Rate-Distortion-Accuracy Tradeoff: JPEG Case Study—0
Uplink Achievable Rate of Intelligent Reflecting Surface-Aided Millimeter-Wave Communications with Low-Resolution ADC and Phase Noise—0
Deep Multi-modality Soft-decoding of Very Low Bit-rate Face Videos—0
FTL: A universal framework for training low-bit DNNs via Feature Transfer—0
High-quality Single-model Deep Video Compression with Frame-Conv3D and Multi-frame Differential Modulation—0
ProxyBNN: Learning Binarized Neural Networks via Proxy Matrices—0
Binarized Neural Network for Single Image Super Resolution—0
Task-Aware Quantization Network for JPEG Image Compression—0
Deep Transferring QuantizationCode1
Show:102550
← PrevPage 151 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