HyperAIHyperAI超神経
ホームプラットフォームドキュメントニュース論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAIHyperAI超神経

Command Palette

Search for a command to run...

Image Classification On Kuzushiji Mnist

評価指標

Accuracy
Error

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

Paper TitleRepository
KMNIST-Tiny99.35-Efficient Global Neural Architecture Search-
KMNIST-Mobile99.29-Efficient Global Neural Architecture Search-
VGG-5 (Spinal FC)99.150.85SpinalNet: Deep Neural Network with Gradual Input
CAMNet399.050.95Context-Aware Multipath Networks-
VGG8B(2x) + LocalLearning + CO99.010.99Training Neural Networks with Local Error Signals
CN(d=32)98.84-Toward Understanding Supervised Representation Learning with RKHS and GAN-
NSRL (log D) (d=16)98.81-Toward Understanding Supervised Representation Learning with RKHS and GAN-
CN(d=16)98.80-Toward Understanding Supervised Representation Learning with RKHS and GAN-
Resnet-15298.79-A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis-
R-ExplaiNet-2698.781.22Learning local discrete features in explainable-by-design convolutional neural networks
ResNet-1498.75-CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters
NSRL (WGAN) (d=32)98.72-Toward Understanding Supervised Representation Learning with RKHS and GAN-
NSRL (WGAN) (d=8)98.68-Toward Understanding Supervised Representation Learning with RKHS and GAN-
NSRL (WGAN) (d=16)98.66-Toward Understanding Supervised Representation Learning with RKHS and GAN-
NSRL (log D) (d=32)98.63-Toward Understanding Supervised Representation Learning with RKHS and GAN-
NSRL (log D) (d=8)98.61-Toward Understanding Supervised Representation Learning with RKHS and GAN-
CN(d=8)98.60-Toward Understanding Supervised Representation Learning with RKHS and GAN-
Efficient Capsnet98.43-Improved efficient capsule network for Kuzushiji-MNIST benchmark dataset classification-
PreActResNet-18 + Input Mixup98.41-mixup: Beyond Empirical Risk Minimization
PreActResNet-1897.82-Identity Mappings in Deep Residual Networks
0 of 26 row(s) selected.