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 4901–4925 of 4925 papers

TitleStatusHype
Random Binary Mappings for Kernel Learning and Efficient SVM—0
K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes—0
Event Retrieval in Large Video Collections with Circulant Temporal Encoding—0
Optimized Product Quantization for Approximate Nearest Neighbor Search—0
Sparse Quantization for Patch Description—0
Learning Binary Codes for High-Dimensional Data Using Bilinear Projections—0
Cartesian K-MeansCode0
Qualitative detection of oil adulteration with machine learning approaches—0
An Adaptive Statistical Non-uniform Quantizer for Detail Wavelet Components in Lossy JPEG2000 Image Compression—0
Anisotropic oracle inequalities in noisy quantization—0
Wavelet-denoising on hardware devices with Perfect Reconstruction, low latency and adaptive thresholding—0
An improved wavelet-based signal-denoising architecture with less hardware consumption—0
Angular Quantization-based Binary Codes for Fast Similarity Search—0
Learning Probability Measures with respect to Optimal Transport Metrics—0
Robust Dequantized Compressive Sensing—0
Codage \'echelonnable \`a granularit\'e fine de la parole : Application au codeur G.729 (Fine granularity scalable speech coding: Application to the G.729 coder) [in French]—0
Joshua 4.0: Packing, PRO, and Paraphrases—0
Improving K-Nearest Neighbor Efficacy for Farsi Text Classification—0
Efficient statistical classification of satellite measurementsCode0
Efficient Match Kernel between Sets of Features for Visual Recognition—0
Group Sparse Coding—0
An Additive Latent Feature Model for Transparent Object Recognition—0
Spectral Clustering with Perturbed Data—0
结合遗传算法的LVQ神经网络 在声学底质分类中的应用—0
Scalable Recognition with a Vocabulary TreeCode0
Show:102550
← PrevPage 99 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