Image Classification On Svhn

Metrics

Percentage error

Results

Performance results of various models on this benchmark

Model Name	Percentage error	Paper Title	Repository
M1+TSVM	54.33	Semi-Supervised Learning with Deep Generative Models
Auxiliary DGN	22.86	Auxiliary Deep Generative Models
ReNet	2.4	ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
EXACT (WRN-16-8)	2.21	EXACT: How to Train Your Accuracy
PBA [ho2019pba]	1.2	Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
DenseNet	1.59	Densely Connected Convolutional Networks
E2E-M3	1.0	Rethinking Recurrent Neural Networks and Other Improvements for Image Classification
DCNN	2.2	Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
MIM	2.0	On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units	-
RCNN-96	1.8	-	-
CMsC	1.8	Competitive Multi-scale Convolution	-
SEER (RegNet10B)	13.6	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
FLSCNN	4.0	Enhanced Image Classification With a Fast-Learning Shallow Convolutional Neural Network	-
DCGAN	22.48	Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Multilevel Residual Networks	1.59	Residual Networks of Residual Networks: Multilevel Residual Networks
ResNet-18	2.65	Benchopt: Reproducible, efficient and collaborative optimization benchmarks
Regularization of Neural Networks using DropConnect	1.9	-	-
Improved GAN	8.11	Improved Techniques for Training GANs
TripleNet-B	-	Efficient Convolutional Neural Networks on Raspberry Pi for Image Classification
BNM NiN	1.8	Batch-normalized Maxout Network in Network

0 of 62 row(s) selected.