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 4451–4500 of 4925 papers

TitleStatusHype
Relaxed Quantization for Discretized Neural NetworksCode0
Post-training 4-bit quantization of convolution networks for rapid-deploymentCode0
Quantization-Aware Phase Retrieval—0
Operation-guided Neural Networks for High Fidelity Data-To-Text Generation—0
ProxQuant: Quantized Neural Networks via Proximal OperatorsCode0
Large Scale Clustering with Variational EM for Gaussian Mixture ModelsCode0
Minimal Random Code Learning: Getting Bits Back from Compressed Model ParametersCode0
Vector Quantized Spectral Clustering applied to Soybean Whole Genome Sequences—0
NICE: Noise Injection and Clamping Estimation for Neural Network QuantizationCode1
Computation-Efficient Quantization Method for Deep Neural Networks—0
The Convergence of Sparsified Gradient Methods—0
Scalar Arithmetic Multiple Data: Customizable Precision 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
High-Accuracy Inference in Neuromorphic Circuits using Hardware-Aware Training—0
Distributed Chernoff Test: Optimal decision systems over networks—0
Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference—0
Operations Guided Neural Networks for High Fidelity Data-To-Text GenerationCode0
Deep Priority HashingCode0
DeepHunter: Hunting Deep Neural Network Defects via Coverage-Guided Fuzzing—0
Double JPEG Detection in Mixed JPEG Quality Factors using Deep Convolutional Neural Network—0
Product Quantization Network for Fast Image Retrieval—0
Learning Compression from Limited Unlabeled DataCode0
LSQ++: Lower running time and higher recall in multi-codebook quantizationCode0
Learning Sparse Low-Precision Neural Networks With Learnable Regularization—0
Hierarchical Quantized Representations for Script GenerationCode0
An Overview of Datatype Quantization Techniques for Convolutional Neural Networks—0
Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss—0
A study on speech enhancement using exponent-only floating point quantized neural network (EOFP-QNN)—0
Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks—0
DNN Feature Map Compression using Learned Representation over GF(2)Code0
Learning Discriminative Hashing Codes for Cross-Modal Retrieval based on Multi-view Features—0
A Survey on Methods and Theories of Quantized Neural Networks—0
Dirichlet Mixture Model based VQ Performance Prediction for Line Spectral Frequency—0
Approximate Probabilistic Neural Networks with Gated Threshold Logic—0
Design Flow of Accelerating Hybrid Extremely Low Bit-width Neural Network in Embedded FPGA—0
DFTerNet: Towards 2-bit Dynamic Fusion Networks for Accurate Human Activity Recognition—0
LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural NetworksCode0
Aggregated Learning: A Deep Learning Framework Based on Information-Bottleneck Vector Quantization—0
Coreset-Based Neural Network Compression—0
StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth PredictionCode0
Performance, Power, and Area Design Trade-offs in Millimeter-Wave Transmitter Beamforming ArchitecturesCode0
Hybrid Scene Compression for Visual Localization—0
Statistical Model Compression for Small-Footprint Natural Language Understanding—0
Defend Deep Neural Networks Against Adversarial Examples via Fixed and Dynamic Quantized Activation Functions—0
Accuracy to Throughput Trade-offs for Reduced Precision Neural Networks on Reconfigurable Logic—0
Bridging the Accuracy Gap for 2-bit Quantized Neural Networks (QNN)—0
Learning Product Codebooks using Vector Quantized Autoencoders for Image Retrieval—0
Deep attention-based classification network for robust depth predictionCode0
Show:102550
← PrevPage 90 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