ResNet-101 (lpf5)

Reported on 6 benchmarks across 2 tasks · 1 paper

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

Methodology3 results

Domain AdaptationonVizWiz-Classification
Accuracy - All Images· 2019-04-25
41
best: 57.2 (VOLO-D5)
Making Convolutional Networks Shift-Invariant Again arXiv:1904.11486
Domain AdaptationonVizWiz-Classification
Accuracy - Clean Images· 2019-04-25
45.8
best: 450 (ViT-8/B-224)
Making Convolutional Networks Shift-Invariant Again arXiv:1904.11486
Domain AdaptationonVizWiz-Classification
Accuracy - Corrupted Images· 2019-04-25
34.8
best: 51.8 (VOLO-D5)
Making Convolutional Networks Shift-Invariant Again arXiv:1904.11486

Computer Vision3 results

Domain GeneralizationonVizWiz-Classification
Accuracy - All Images· 2019-04-25
41
best: 57.2 (VOLO-D5)
Making Convolutional Networks Shift-Invariant Again arXiv:1904.11486
Domain GeneralizationonVizWiz-Classification
Accuracy - Clean Images· 2019-04-25
45.8
best: 450 (ViT-8/B-224)
Making Convolutional Networks Shift-Invariant Again arXiv:1904.11486
Domain GeneralizationonVizWiz-Classification
Accuracy - Corrupted Images· 2019-04-25
34.8
best: 51.8 (VOLO-D5)
Making Convolutional Networks Shift-Invariant Again arXiv:1904.11486