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 2851–2900 of 4925 papers

TitleStatusHype
Communication-Efficient Adaptive Federated LearningCode1
MemSE: Fast MSE Prediction for Noisy Memristor-Based DNN Accelerators—0
BMInf: An Efficient Toolkit for Big Model Inference and TuningCode2
Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization—0
Deep Geometry Post-Processing for Decompressed Point CloudsCode1
RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training QuantizationCode1
Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications—0
Federated Learning with Lossy Distributed Source Coding: Analysis and Optimization—0
Improving Self-Supervised Learning-based MOS Prediction NetworksCode0
A Tale of Two Models: Constructing Evasive Attacks on Edge ModelsCode0
Arbitrary Bit-width Network: A Joint Layer-Wise Quantization and Adaptive Inference Approach—0
How to Attain Communication-Efficient DNN Training? Convert, Compress, Correct—0
Unconditional Image-Text Pair Generation with Multimodal Cross QuantizerCode0
INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold—0
Composite Code Sparse Autoencoders for first stage retrieval—0
Secure Formation Control via Edge Computing Enabled by Fully Homomorphic Encryption and Mixed Uniform-Logarithmic Quantization—0
Joint Coreset Construction and Quantization for Distributed Machine Learning—0
Non-asymptotic spectral bounds on the -entropy of kernel classes—0
Channel Pruning In Quantization-aware Training: An Adaptive Projection-gradient Descent-shrinkage-splitting Method—0
Deep Learning-Based Intra Mode Derivation for Versatile Video Coding—0
Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization—0
Characterizing and Understanding the Behavior of Quantized Models for Reliable DeploymentCode0
Unsupervised Quantized Prosody Representation for Controllable Speech Synthesis—0
Bimodal Distributed Binarized Neural NetworksCode0
Soft Threshold Ternary NetworksCode1
BigDL 2.0: Seamless Scaling of AI Pipelines from Laptops to Distributed ClusterCode5
Cancer Subtyping via Embedded Unsupervised Learning on Transcriptomics Data—0
Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense EmbeddingsCode1
Scaling Language Model Size in Cross-Device Federated Learning—0
It's All In the Teacher: Zero-Shot Quantization Brought Closer to the TeacherCode1
Ternary and Binary Quantization for Improved Classification—0
Autoregressive Co-Training for Learning Discrete Speech RepresentationsCode0
4-bit Conformer with Native Quantization Aware Training for Speech RecognitionCode2
Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking—0
Eventor: An Efficient Event-Based Monocular Multi-View Stereo Accelerator on FPGA Platform—0
Reverse Link Analysis for Full-Duplex Cellular Networks with Low Resolution ADC/DAC—0
New pyramidal hybrid textural and deep features based automatic skin cancer classification model: Ensemble DarkNet and textural feature extractor—0
REx: Data-Free Residual Quantization Error Expansion—0
SPIQ: Data-Free Per-Channel Static Input Quantization—0
Pseudo-Label Transfer from Frame-Level to Note-Level in a Teacher-Student Framework for Singing Transcription from Polyphonic MusicCode1
LAMBDA: Covering the Solution Set of Black-Box Inequality by Search Space Quantization—0
FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning SimulationsCode1
MKQ-BERT: Quantized BERT with 4-bits Weights and Activations—0
Efficient-VDVAE: Less is moreCode1
Mokey: Enabling Narrow Fixed-Point Inference for Out-of-the-Box Floating-Point Transformer Models—0
Fast on-line signature recognition based on VQ with time modeling—0
FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation—0
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and QuantizationCode1
Overcoming Oscillations in Quantization-Aware TrainingCode1
Compression of Generative Pre-trained Language Models via Quantization—0
Show:102550
← PrevPage 58 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