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 3976–4000 of 4925 papers

TitleStatusHype
Breaking the waves: asymmetric random periodic features for low-bitrate kernel machines—0
Depthwise Discrete Representation LearningCode0
Exposing Hardware Building Blocks to Machine Learning Frameworks—0
Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training—0
Unsupervised Person Re-identification via Softened Similarity LearningCode0
Deep Attentive Generative Adversarial Network for Photo-Realistic Image De-Quantization—0
CNN2Gate: Toward Designing a General Framework for Implementation of Convolutional Neural Networks on FPGA—0
Attentive One-Dimensional Heatmap Regression for Facial Landmark Detection and Tracking—0
Distributed Inference with Sparse and Quantized Communication—0
A Modular Neural Network Based Deep Learning Approach for MIMO Signal Detection—0
Improved Gradient based Adversarial Attacks for Quantized NetworksCode0
Deep Learning for Radio Resource Allocation with Diverse Quality-of-Service Requirements in 5G—0
Event-Triggered Quantized Average Consensus via Mass Summation—0
A Short Note on Analyzing Sequence Complexity in Trajectory Prediction Benchmarks—0
Acceleration of Convolutional Neural Network Using FFT-Based Split Convolutions—0
A Survey of Methods for Low-Power Deep Learning and Computer Vision—0
Tree Index: A New Cluster Evaluation Technique—0
Multi-Feature Discrete Collaborative Filtering for Fast Cold-start Recommendation—0
Multi-target regression via output space quantization—0
DP-Net: Dynamic Programming Guided Deep Neural Network Compression—0
FTT-NAS: Discovering Fault-Tolerant Convolutional Neural ArchitectureCode0
LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units—0
Efficient Bitwidth Search for Practical Mixed Precision Neural Network—0
RCNet: Incorporating Structural Information into Deep RNN for MIMO-OFDM Symbol Detection with Limited Training—0
LCP: A Low-Communication Parallelization Method for Fast Neural Network Inference in Image Recognition—0
Show:102550
← PrevPage 160 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