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 4726–4750 of 4925 papers

TitleStatusHype
ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMsCode0
Web-Scale Image Clustering RevisitedCode0
Efficient course recommendations with T5-based ranking and summarizationCode0
Image Hashing by Minimizing Discrete Component-wise Wasserstein DistanceCode0
Post-training 4-bit quantization of convolution networks for rapid-deploymentCode0
Post training 4-bit quantization of convolutional networks for rapid-deploymentCode0
A Resource-Efficient Embedded Iris Recognition System Using Fully Convolutional NetworksCode0
Post-training Model Quantization Using GANs for Synthetic Data GenerationCode0
VecQ: Minimal Loss DNN Model Compression With Vectorized Weight QuantizationCode0
Post-Training Quantization for 3D Medical Image Segmentation: A Practical Study on Real Inference EnginesCode0
Causal-DFQ: Causality Guided Data-free Network QuantizationCode0
REMIND Your Neural Network to Prevent Catastrophic ForgettingCode0
Remote Inference over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector QuantizationCode0
Identifying and Clustering Counter Relationships of Team Compositions in PvP Games for Efficient Balance AnalysisCode0
Efficient computation of counterfactual explanations of LVQ modelsCode0
Post-Training Quantization for Re-parameterization via Coarse & Fine Weight SplittingCode0
RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via RepeatingCode0
Efficient CNN-LSTM based Image Captioning using Neural Network CompressionCode0
DAQ: Density-Aware Post-Training Weight-Only Quantization For LLMsCode0
A Quantization-Friendly Separable Convolution for MobileNetsCode0
IBVC: Interpolation-driven B-frame Video CompressionCode0
Focused Quantization for Sparse CNNsCode0
CUCL: Codebook for Unsupervised Continual LearningCode0
Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation RelaxingCode0
Hyper-Sphere Quantization: Communication-Efficient SGD for Federated LearningCode0
Show:102550
← PrevPage 190 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