ResNet-9

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 ClassificationonCIFAR-10
Percentage correct· uses extra data· 2022-03-29
94.79
best: 99.5 (ViT-H/14)
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters arXiv:2203.15331
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2022-03-29
75.59
best: 96.08 (EffNet-L2 (SAM))
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters arXiv:2203.15331
Image ClassificationonMNIST
Accuracy· 2022-03-29
99.68
best: 99.87 (Branching/Merging CNN + Homogeneous Vector Capsules)
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters arXiv:2203.15331