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 4751–4775 of 4925 papers

TitleStatusHype
Learning Succinct Models: Pipelined Compression with L1-Regularization, Hashing, Elias-Fano Indices, and Quantization—0
Clustering with Bregman Divergences: an Asymptotic Analysis—0
Effective Quantization Methods for Recurrent Neural NetworksCode0
Fast Supervised Discrete Hashing and its AnalysisCode0
Deep Quantization: Encoding Convolutional Activations with Deep Generative Model—0
Recurrent Neural Networks With Limited Numerical PrecisionCode0
Efficient Convolutional Neural Network with Binary Quantization Layer—0
Quantized neural network design under weight capacity constraint—0
The ZipML Framework for Training Models with End-to-End Low Precision: The Cans, the Cannots, and a Little Bit of Deep LearningCode0
Associative Memories to Accelerate Approximate Nearest Neighbor Search—0
Distributed Mean Estimation with Limited Communication—0
Accurate Deep Representation Quantization with Gradient Snapping Layer for Similarity Search—0
End-to-end Learning of Deep Visual Representations for Image RetrievalCode0
Structured adaptive and random spinners for fast machine learning computations—0
Federated Learning: Strategies for Improving Communication Efficiency—0
QSGD: Communication-Efficient SGD via Gradient Quantization and EncodingCode0
Reliability of PET/CT shape and heterogeneity features in functional and morphological components of Non-Small Cell Lung Cancer tumors: a repeatability analysis in a prospective multi-center cohort—0
Fast learning rates with heavy-tailed losses—0
Online Categorical Subspace Learning for Sketching Big Data with Misses—0
On Randomized Distributed Coordinate Descent with Quantized Updates—0
Generalized residual vector quantization for large scale data—0
Discovering Patterns in Time-Varying Graphs: A Triclustering Approach—0
Approximate search with quantized sparse representations—0
A 58.6mW Real-Time Programmable Object Detector with Multi-Scale Multi-Object Support Using Deformable Parts Model on 1920x1080 Video at 30fps—0
End-to-end optimization of nonlinear transform codes for perceptual quality—0
Show:102550
← PrevPage 191 of 197Next →
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