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 3401–3450 of 4925 papers

TitleStatusHype
Robustness Analysis of Deep Learning Frameworks on Mobile PlatformsCode0
Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework—0
iRNN: Integer-only Recurrent Neural Network—0
QTTNet: Quantized Tensor Train Neural Networks for 3D Object and Video Recognition.Code0
Channel Estimation in MIMO Systems with One-bit Spatial Sigma-delta ADCs—0
Experimental implementation of a neural network optical channel equalizer in restricted hardware using pruning and quantization—0
Revisiting Quantization Error in Face Alignment—0
2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency—0
PHPQ: Pyramid Hybrid Pooling Quantization for Efficient Fine-Grained Image Retrieval—0
1st-Order Dynamics on Nonlinear Agents for Resource Allocation over Uniformly-Connected Networks—0
Bag of Tricks for Optimizing Transformer EfficiencyCode0
ECQ^x: Explainability-Driven Quantization for Low-Bit and Sparse DNNsCode0
Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks—0
Self-supervised Product Quantization for Deep Unsupervised Image RetrievalCode0
Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss—0
Risk Assessment for Connected Vehicles under Stealthy Attacks on Vehicle-to-Vehicle Networks—0
Characterization of the frequency response of channel-interleaved photonic ADCs based on the optical time-division demultiplexer—0
Quantized Convolutional Neural Networks Through the Lens of Partial Differential Equations—0
Quantization of Generative Adversarial Networks for Efficient Inference: a Methodological Study—0
4-bit Quantization of LSTM-based Speech Recognition Models—0
A Quantitative Approach To The Temporal Dependency in Video Coding—0
On Adaptive Transmission for Distributed Detection in Energy Harvesting Wireless Sensor Networks with Limited Fusion Center Feedback—0
Rate distortion comparison of a few gradient quantizers—0
On the Acceleration of Deep Neural Network Inference using Quantized Compressed Sensing—0
Reconfigurable co-processor architecture with limited numerical precision to accelerate deep convolutional neural networks—0
Integer-arithmetic-only Certified Robustness for Quantized Neural Networks—0
Quantization Backdoors to Deep Learning Commercial Frameworks—0
Deployment of Deep Neural Networks for Object Detection on Edge AI Devices with Runtime Optimization—0
Verifying Low-dimensional Input Neural Networks via Input Quantization—0
Distance-aware Quantization—0
Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devicesCode0
Audio Spectral Enhancement: Leveraging Autoencoders for Low Latency Reconstruction of Long, Lossy Audio SequencesCode0
Energy Efficiency Maximization Precoding for Quantized Massive MIMO Systems—0
Bifocal Neural ASR: Exploiting Keyword Spotting for Inference Optimization—0
MOHAQ: Multi-Objective Hardware-Aware Quantization of Recurrent Neural Networks—0
All-Digital LoS MIMO with Low-Precision Analog-to-Digital Conversion—0
Communication-Efficient Federated Learning via Predictive CodingCode0
Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search—0
DQ-SGD: Dynamic Quantization in SGD for Communication-Efficient Distributed Learning—0
Sparse Joint Transmission for Cloud Radio Access Networks with Limited Fronthaul Capacity—0
Local Morphometry of Closed, Implicit Surfaces—0
QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning—0
Adaptive Precision Training (AdaPT): A dynamic fixed point quantized training approach for DNNs—0
DV-Det: Efficient 3D Point Cloud Object Detection with Dynamic Voxelization—0
High-Dimensional Distribution Generation Through Deep Neural Networks—0
Deep Learning for Estimation and Pilot Signal Design in Few-Bit Massive MIMO Systems—0
HYPER-SNN: Towards Energy-efficient Quantized Deep Spiking Neural Networks for Hyperspectral Image Classification—0
Finite-Bit Quantization For Distributed Algorithms With Linear Convergence—0
Pruning Ternary Quantization—0
HARP-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding—0
Show:102550
← PrevPage 69 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