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 4451–4475 of 4925 papers

TitleStatusHype
A Flexible, Extensible Software Framework for Neural Net Compression—0
Differentiable Training for Hardware Efficient LightNNs—0
CNN inference acceleration using dictionary of centroids—0
Low-bit quantization and quantization-aware training for small-footprint keyword spotting—0
Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction—0
Quantization for Rapid Deployment of Deep Neural Networks—0
Predictive Uncertainty through Quantization—0
A Novel Chaotic Uniform Quantizer for Speech Coding—0
Is PGD-Adversarial Training Necessary? Alternative Training via a Soft-Quantization Network with Noisy-Natural Samples OnlyCode0
Rate Distortion For Model Compression: From Theory To Practice—0
Robust identification of thermal models for in-production High-Performance-Computing clusters with machine learning-based data selection—0
Relaxed Quantization for Discretized Neural NetworksCode0
Quantization-Aware Phase Retrieval—0
Post-training 4-bit quantization of convolution networks for rapid-deploymentCode0
ProxQuant: Quantized Neural Networks via Proximal OperatorsCode0
Large Scale Clustering with Variational EM for Gaussian Mixture ModelsCode0
Operation-guided Neural Networks for High Fidelity Data-To-Text Generation—0
Minimal Random Code Learning: Getting Bits Back from Compressed Model ParametersCode0
Vector Quantized Spectral Clustering applied to Soybean Whole Genome Sequences—0
The Convergence of Sparsified Gradient Methods—0
Scalar Arithmetic Multiple Data: Customizable Precision for Deep Neural Networks—0
Computation-Efficient Quantization Method for Deep Neural Networks—0
Deep residual network for steganalysis of digital imagesCode0
Sparsified SGD with MemoryCode0
Deep Compressive Autoencoder for Action Potential Compression in Large-Scale Neural RecordingCode0
Show:102550
← PrevPage 179 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