R-ExplaiNet-22 (single model)

Reported on 3 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Image ClassificationonMNIST
Accuracy· 2024-10-31
99.8
best: 99.87 (Branching/Merging CNN + Homogeneous Vector Capsules)
Learning local discrete features in explainable-by-design convolutional neural networks arXiv:2411.00139
Image ClassificationonMNIST
Percentage error· 2024-10-31
0.2
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
Learning local discrete features in explainable-by-design convolutional neural networks arXiv:2411.00139
Image ClassificationonMNIST
Trainable Parameters· 2024-10-31
743882
best: 1882602 (Neural Architecture Search (NAS)-enabled Convolutional Neural Network (CNN))
Learning local discrete features in explainable-by-design convolutional neural networks arXiv:2411.00139