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

Showing 48514900 of 4925 papers

TitleStatusHype
Simultaneous Feature Learning and Hash Coding with Deep Neural Networks0
Some Further Evidence about Magnification and Shape in Neural Gas0
Quantized Nonparametric Estimation over Sobolev Ellipsoids0
Variational Optimization of Annealing Schedules0
Vector Quantization by Minimizing Kullback-Leibler Divergence0
Pairwise Rotation Hashing for High-dimensional Features0
Face recognition using color local binary pattern from mutually independent color channels0
Compressing Deep Convolutional Networks using Vector Quantization0
Background Modelling using Octree Color Quantization0
Hashing on Nonlinear Manifolds0
Quantized Kernel Learning for Feature Matching0
Self-Adaptable Templates for Feature Coding0
Speaker Identification From Youtube Obtained Data0
Stacked Quantizers for Compositional Vector CompressionCode0
Efficient multivariate sequence classification0
Fast Low-rank Representation based Spatial Pyramid Matching for Image Classification0
Seeing through bag-of-visual-word glasses: towards understanding quantization effects in feature extraction methods0
Lightweight Client-Side Chinese/Japanese Morphological Analyzer Based on Online LearningCode0
Object Proposal Generation using Two-Stage Cascade SVMs0
Efficient On-the-fly Category Retrieval using ConvNets and GPUs0
User Modeling by Using Bag-of-Behaviors for Building a Dialog System Sensitive to the Interlocutor's Internal State0
Two-Stage Hashing for Fast Document Retrieval0
Learning Receptive Fields for Pooling from Tensors of Feature Response0
Locally Optimized Product Quantization for Approximate Nearest Neighbor Search0
Compact Representation for Image Classification: To Choose or to Compress?0
Additive Quantization for Extreme Vector Compression0
Locally Linear Hashing for Extracting Non-Linear Manifolds0
Distance Encoded Product Quantization0
A Compact and Discriminative Face Track Descriptor0
Optimized Cartesian K-Means0
Improving Bilayer Product Quantization for Billion-Scale Approximate Nearest Neighbors in High Dimensions0
Coding for Random Projections and Approximate Near Neighbor Search0
Parallel WiSARD object tracker: a ram-based tracking system0
Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval0
Precision Enhancement of 3D Surfaces from Multiple Compressed Depth Maps0
Packing and Padding: Coupled Multi-index for Accurate Image Retrieval0
Learning Mid-Level Features and Modeling Neuron Selectivity for Image Classification0
Stopping Rules for Bag-of-Words Image Search and Its Application in Appearance-Based Localization0
Codebook based Audio Feature Representation for Music Information Retrieval0
mARC: Memory by Association and Reinforcement of Contexts0
Which Space Partitioning Tree to Use for Search?0
Fast Template Evaluation with Vector Quantization0
Reduplication across Categories in Cantonese0
Two Dimensional Array Imaging with Beam Steered Data0
Regularization in Relevance Learning Vector Quantization Using l one Norms0
An Application of Backpropagation Artificial Neural Network Method for Measuring The Severity of Osteoarthritis0
An Efficient Index for Visual Search in Appearance-based SLAM0
Using Self-Organizing Maps for Sentiment Analysis0
A Study on Unsupervised Dictionary Learning and Feature Encoding for Action Classification0
Coding for Random Projections0
Show:102550
← PrevPage 98 of 99Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FQ-ViT (ViT-L)Top-1 Accuracy (%)85.03Unverified
2FQ-ViT (ViT-B)Top-1 Accuracy (%)83.31Unverified
3FQ-ViT (Swin-B)Top-1 Accuracy (%)82.97Unverified
4FQ-ViT (Swin-S)Top-1 Accuracy (%)82.71Unverified
5FQ-ViT (DeiT-B)Top-1 Accuracy (%)81.2Unverified
6FQ-ViT (Swin-T)Top-1 Accuracy (%)80.51Unverified
7FQ-ViT (DeiT-S)Top-1 Accuracy (%)79.17Unverified
8Xception W8A8Top-1 Accuracy (%)78.97Unverified
9ADLIK-MO-ResNet50-W4A4Top-1 Accuracy (%)77.88Unverified
10ADLIK-MO-ResNet50-W3A4Top-1 Accuracy (%)77.34Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_3MAP160,327.04Unverified
2DTQMAP0.79Unverified
#ModelMetricClaimedVerifiedStatus
1OutEffHop-Bert_basePerplexity6.3Unverified
2OutEffHop-Bert_basePerplexity6.21Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy98.13Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy92.92Unverified
#ModelMetricClaimedVerifiedStatus
1SSD ResNet50 V1 FPN 640x640MAP34.3Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-495.13Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-496.38Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_5All84,809,664Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy99.8Unverified