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 801–850 of 4925 papers

TitleStatusHype
Searching for Low-Bit Weights in Quantized Neural NetworksCode1
Learning a Single Model with a Wide Range of Quality Factors for JPEG Image Artifacts RemovalCode1
Heatmap Regression via Randomized RoundingCode1
GAN Slimming: All-in-One GAN Compression by A Unified Optimization FrameworkCode1
PROFIT: A Novel Training Method for sub-4-bit MobileNet ModelsCode1
Deep Transferring QuantizationCode1
Geometric Total Variation for Image Vectorization, Zooming and Pixel Art DepixelizingCode1
HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNsCode1
Resolution Switchable Networks for Runtime Efficient Image RecognitionCode1
Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data AugmentationCode1
Channel-Level Variable Quantization Network for Deep Image CompressionCode1
AQD: Towards Accurate Fully-Quantized Object DetectionCode1
FracBits: Mixed Precision Quantization via Fractional Bit-WidthsCode1
Deep PeNSieve: A deep learning framework based on the posit number systemCode1
EasyQuant: Post-training Quantization via Scale OptimizationCode1
Graph Convolutional Network for Recommendation with Low-pass Collaborative FiltersCode1
Making DensePose fast and lightCode1
Unsupervised Cross-lingual Representation Learning for Speech RecognitionCode1
FrostNet: Towards Quantization-Aware Network Architecture SearchCode1
APQ: Joint Search for Network Architecture, Pruning and Quantization PolicyCode1
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectorsCode1
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer ProgrammingCode1
VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architectureCode1
UVeQFed: Universal Vector Quantization for Federated LearningCode1
Position-based Scaled Gradient for Model Quantization and PruningCode1
TinyLSTMs: Efficient Neural Speech Enhancement for Hearing AidsCode1
MicroNet for Efficient Language ModelingCode1
Bi3D: Stereo Depth Estimation via Binary ClassificationsCode1
Bayesian Bits: Unifying Quantization and PruningCode1
Data-Free Network Quantization With Adversarial Knowledge DistillationCode1
A Little Bit More: Bitplane-Wise Bit-Depth RecoveryCode1
Lite Transformer with Long-Short Range AttentionCode1
LSQ+: Improving low-bit quantization through learnable offsets and better initializationCode1
Technical Report: NEMO DNN Quantization for Deployment ModelCode1
Minimizing FLOPs to Learn Efficient Sparse RepresentationsCode1
LogicNets: Co-Designed Neural Networks and Circuits for Extreme-Throughput ApplicationsCode1
Feature Quantization Improves GAN TrainingCode1
Single-Image HDR Reconstruction by Learning to Reverse the Camera PipelineCode1
Learning to Structure an Image with Few ColorsCode1
DNN+NeuroSim V2.0: An End-to-End Benchmarking Framework for Compute-in-Memory Accelerators for On-chip TrainingCode1
Fast Distance-based Anomaly Detection in Images Using an Inception-like AutoencoderCode1
Generative Low-bitwidth Data Free QuantizationCode1
Ternary Compression for Communication-Efficient Federated LearningCode1
Probability Weighted Compact Feature for Domain Adaptive RetrievalCode1
VQ-DRAW: A Sequential Discrete VAECode1
Automatic Perturbation Analysis for Scalable Certified Robustness and BeyondCode1
Generalized Product Quantization Network for Semi-supervised Image RetrievalCode1
Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of TransformersCode1
Searching for Winograd-aware Quantized NetworksCode1
Exploring the Connection Between Binary and Spiking Neural NetworksCode1
Show:102550
← PrevPage 17 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