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 3851–3900 of 4925 papers

TitleStatusHype
An Overview of Neural Network Compression—0
Exploring the Potential of Low-bit Training of Convolutional Neural Networks—0
Semi-Blind Post-Equalizer SINR Estimation and Dual CSI Feedback for Radar-Cellular Coexistence—0
Joint Texture and Geometry Optimization for RGB-D Reconstruction—0
Fixed-Point Back-Propagation Training—0
Rotation Consistent Margin Loss for Efficient Low-Bit Face Recognition—0
Quantized Neural Networks: Characterization and Holistic Optimization—0
LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery—0
Task-Oriented Data Compression for Multi-Agent Communications Over Bit-Budgeted Channels—0
A Feature-map Discriminant Perspective for Pruning Deep Neural Networks—0
Quantifying the Complexity of Standard Benchmarking Datasets for Long-Term Human Trajectory Prediction—0
Accelerating Neural Network Inference by Overflow Aware Quantization—0
Local Motion Planner for Autonomous Navigation in Vineyards with a RGB-D Camera-Based Algorithm and Deep Learning Synergy—0
Position-based Scaled Gradient for Model Quantization and PruningCode1
Conditionally Deep Hybrid Neural Networks Across Edge and Cloud—0
Supervised Learning in the Presence of Concept Drift: A modelling framework—0
TinyLSTMs: Efficient Neural Speech Enhancement for Hearing AidsCode1
BiQGEMM: Matrix Multiplication with Lookup Table For Binary-Coding-based Quantized DNNs—0
Energy Efficiency Optimization for Millimeter Wave System with Resolution-Adaptive ADCs—0
Attention-based Transducer for Online Speech Recognition—0
VecQ: Minimal Loss DNN Model Compression With Vectorized Weight QuantizationCode0
Learning on a Grassmann Manifold: CSI Quantization for Massive MIMO Systems—0
Low-Complexity Vector Quantized Compressed Sensing via Deep Neural Networks—0
MicroNet for Efficient Language ModelingCode1
HVS-Based Perceptual Color Compression of Image Data—0
Massive MIMO Channel Estimation with Low-Resolution Spatial Sigma-Delta ADCs—0
Efficient Federated Learning over Multiple Access Channel with Differential Privacy Constraints—0
A flexible, extensible software framework for model compression based on the LC algorithm—0
A Reconstruction-Computation-Quantization (RCQ) Approach to Node Operations in LDPC Decoding—0
Bi3D: Stereo Depth Estimation via Binary ClassificationsCode1
Bayesian Bits: Unifying Quantization and PruningCode1
Prive-HD: Privacy-Preserved Hyperdimensional Computing—0
What if Adversarial Samples were Digital ImagesCode0
GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference—0
Data-Free Network Quantization With Adversarial Knowledge DistillationCode1
SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation—0
WSMN: An optimized multipurpose blind watermarking in Shearlet domain using MLP and NSGA-II—0
Visualisation and knowledge discovery from interpretable models—0
The Bussgang Decomposition of Non-Linear Systems: Basic Theory and MIMO Extensions—0
An Experimental Study of Reduced-Voltage Operation in Modern FPGAs for Neural Network Acceleration—0
CDC: Classification Driven Compression for Bandwidth Efficient Edge-Cloud Collaborative Deep Learning—0
Deep Neural Network-Based Quantized Signal Reconstruction for DOA Estimation—0
A Little Bit More: Bitplane-Wise Bit-Depth RecoveryCode1
Linear Symmetric Quantization of Neural Networks for Low-precision Integer Hardware—0
General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference—0
Quantized Adam with Error Feedback—0
Dynamic Quantized Consensus of General Linear Multi-agent Systems under Denial-of-Service Attacks—0
Streamlining Tensor and Network Pruning in PyTorch—0
Automatic low-bit hybrid quantization of neural networks through meta learning—0
Quantization of Deep Neural Networks for Accumulator-constrained Processors—0
Show:102550
← PrevPage 78 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