Tree+Max-Avg pooling

Reported on 4 benchmarks across 1 task · 1 paper · 1 SOTA

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

Computer Vision4 results

Image ClassificationonSVHN
Percentage error· 2015-09-30
1.7
best: 1 (E2E-M3)
SOTA
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree arXiv:1509.08985
Image ClassificationonCIFAR-10
Percentage correct· 2015-09-30
94
best: 99.5 (ViT-H/14)
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree arXiv:1509.08985
Image ClassificationonCIFAR-100
Percentage correct· 2015-09-30
67.6
best: 96.08 (EffNet-L2 (SAM))
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree arXiv:1509.08985
Image ClassificationonMNIST
Percentage error· 2015-09-30
0.3
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree arXiv:1509.08985