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 4576–4600 of 4925 papers

TitleStatusHype
Bernoulli Embeddings for Graphs—0
A Quantization-Friendly Separable Convolution for MobileNetsCode0
Gradient Descent Quantizes ReLU Network Features—0
Incremental Color Quantization for Color-Vision-Deficient Observers Using Mobile Gaming Data—0
Unsupervised Semantic Deep Hashing—0
Word2Bits - Quantized Word VectorsCode0
Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial ExamplesCode0
Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation—0
High-Accuracy Low-Precision TrainingCode0
ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range ContentCode0
Deep Neural Network Compression with Single and Multiple Level QuantizationCode0
Hyperdrive: A Multi-Chip Systolically Scalable Binary-Weight CNN Inference Engine—0
Learning-Based Dequantization For Image Restoration Against Extremely Poor Illumination—0
XNORBIN: A 95 TOp/s/W Hardware Accelerator for Binary Convolutional Neural Networks—0
Scalar Quantization as Sparse Least Square Optimization—0
L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks—0
Loss-aware Weight Quantization of Deep NetworksCode0
Autoencoder based image compression: can the learning be quantization independent?—0
3LC: Lightweight and Effective Traffic Compression for Distributed Machine Learning—0
Low complexity convolutional neural network for vessel segmentation in portable retinal diagnostic devices—0
Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation—0
Simultaneous Compression and Quantization: A Joint Approach for Efficient Unsupervised Hashing—0
Model compression via distillation and quantizationCode0
RNN-SM: Fast Steganalysis of VoIP Streams Using Recurrent Neural NetworkCode0
Compressive Sensing Using Iterative Hard Thresholding with Low Precision Data Representation: Theory and Applications—0
Show:102550
← PrevPage 184 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