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 4301–4350 of 4925 papers

TitleStatusHype
DeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression—0
Compressing Weight-updates for Image Artifacts Removal Neural Networks—0
MobiVSR: A Visual Speech Recognition Solution for Mobile Devices—0
Two-layer Near-lossless HDR Coding with Backward Compatibility to JPEG—0
2-bit Model Compression of Deep Convolutional Neural Network on ASIC Engine for Image Retrieval—0
Reconstruction of Privacy-Sensitive Data from Protected Templates—0
SinReQ: Generalized Sinusoidal Regularization for Low-Bitwidth Deep Quantized Training—0
Efficient Discrete Supervised Hashing for Large-scale Cross-modal Retrieval—0
Compression of Acoustic Event Detection Models with Low-rank Matrix Factorization and Quantization Training—0
Toward Extremely Low Bit and Lossless Accuracy in DNNs with Progressive ADMM—0
Analysis of Quantized Models—0
N-Ary Quantization for CNN Model Compression and Inference Acceleration—0
Double Viterbi: Weight Encoding for High Compression Ratio and Fast On-Chip Reconstruction for Deep Neural Network—0
Nested Dithered Quantization for Communication Reduction in Distributed Training—0
ACIQ: Analytical Clipping for Integer Quantization of neural networksCode0
Dimension-Free Bounds for Low-Precision Training—0
Adaptive Sample-space & Adaptive Probability coding: a neural-network based approach for compression—0
Unsupervised automatic classification of Scanning Electron Microscopy (SEM) images of CD4+ cells with varying extent of HIV virion infection—0
Design Automation for Efficient Deep Learning Computing—0
Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural NetworksCode0
Learning Physical-Layer Communication with Quantized FeedbackCode0
Low Resolution Digital-to-Analog Converter with Digital Dithering for MIMO Transmitter—0
Query-Adaptive Hash Code Ranking for Large-Scale Multi-View Visual Search—0
Rate-Loss Mitigation for a Millimeter-Wave Beamspace MIMO Lens Antenna Array System Using a Hybrid Beam-Selection Scheme—0
Defensive Quantization: When Efficiency Meets Robustness—0
MorphIC: A 65-nm 738k-Synapse/mm^2 Quad-Core Binary-Weight Digital Neuromorphic Processor with Stochastic Spike-Driven Online Learning—0
Matrix and tensor decompositions for training binary neural networks—0
Risk Bounds for Learning Multiple Components with Permutation-Invariant Losses—0
Shared Predictive Cross-Modal Deep Quantization—0
YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving—0
Enhancing Bridge Deck Delamination Detection Based on Aerial Thermography Through Grayscale Morphologic Reconstruction: A Case Study—0
Improved training of binary networks for human pose estimation and image recognition—0
FLightNNs: Lightweight Quantized Deep Neural Networks for Fast and Accurate Inference—0
3DQ: Compact Quantized Neural Networks for Volumetric Whole Brain Segmentation—0
Sublinear quantum algorithms for training linear and kernel-based classifiers—0
Progressive Stochastic Binarization of Deep NetworksCode0
VideoBERT: A Joint Model for Video and Language Representation LearningCode0
Task Oriented Channel State Information Quantization—0
Asymmetric Deep Semantic Quantization for Image Retrieval—0
Lattice Functions for the Analysis of Analog-to-Digital Conversion—0
Understanding Unconventional Preprocessors in Deep Convolutional Neural Networks for Face Identification—0
Training Quantized Neural Networks with a Full-precision Auxiliary Module—0
Robustness of Neural Networks to Parameter Quantization—0
Local Orthogonal Decomposition for Maximum Inner Product Search—0
Variational Inference with Latent Space Quantization for Adversarial ResilienceCode0
Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMMCode0
Deep Learning on Mobile Devices - A Review—0
Learning Convolutional Transforms for Lossy Point Cloud Geometry CompressionCode0
Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural NetworksCode0
Galaxy classification: A machine learning analysis of GAMA catalogue data—0
Show:102550
← PrevPage 87 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