HyperAI超神经

Traffic Sign Recognition On Gtsrb

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
CNN with 3 Spatial Transformers	99.71%	Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods
Sill-Net	99.68%	Sill-Net: Feature Augmentation with Separated Illumination Representation
SeqNet	99.66%	SeqNet: Sequential Networks for One-Shot Traffic Sign Recognition With Transfer Learning
MicronNet (fp16)	98.9%	MicronNet: A Highly Compact Deep Convolutional Neural Network Architecture for Real-time Embedded Traffic Sign Classification
SEER (RegNet10B)	90.71%	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision

0 of 5 row(s) selected.

HyperAI超神经

Traffic Sign Recognition On Gtsrb

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
CNN with 3 Spatial Transformers	99.71%	Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods
Sill-Net	99.68%	Sill-Net: Feature Augmentation with Separated Illumination Representation
SeqNet	99.66%	SeqNet: Sequential Networks for One-Shot Traffic Sign Recognition With Transfer Learning
MicronNet (fp16)	98.9%	MicronNet: A Highly Compact Deep Convolutional Neural Network Architecture for Real-time Embedded Traffic Sign Classification
SEER (RegNet10B)	90.71%	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision

0 of 5 row(s) selected.