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 4676–4700 of 4925 papers

TitleStatusHype
Joint Maximum Purity Forest with Application to Image Super-ResolutionCode0
Performance Guaranteed Network Acceleration via High-Order Residual Quantization—0
Neural Networks Compression for Language Modeling—0
Deep Neural Network Capacity—0
SUBIC: A supervised, structured binary code for image search—0
Learning Accurate Low-Bit Deep Neural Networks with Stochastic QuantizationCode0
Monocular Depth Estimation with Hierarchical Fusion of Dilated CNNs and Soft-Weighted-Sum InferenceCode0
ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning—0
Learning Bag-of-Features Pooling for Deep Convolutional Neural NetworksCode0
Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM—0
Model compression as constrained optimization, with application to neural nets. Part II: quantization—0
A multi-layer image representation using Regularized Residual Quantization: application to compression and denoising—0
Model compression as constrained optimization, with application to neural nets. Part I: general framework—0
Weighted-Entropy-Based Quantization for Deep Neural Networks—0
Product Split Trees—0
Learning Deep Binary Descriptor With Multi-Quantization—0
Deep Visual-Semantic Quantization for Efficient Image Retrieval—0
Bolt: Accelerated Data Mining with Fast Vector CompressionCode2
Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks—0
Representation Learning using Event-based STDP—0
Gradient Diversity: a Key Ingredient for Scalable Distributed Learning—0
SEP-Nets: Small and Effective Pattern Networks—0
ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural NetworksCode0
3D Pathfinding and Collision Avoidance Using Uneven Search-space Quantization and Visual Cone Search—0
Image Compression Based on Compressive Sensing: End-to-End Comparison with JPEG—0
Show:102550
← PrevPage 188 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