TransBoost-ResNet50

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 ClassificationonDTD
Accuracy· uses extra data· 2022-05-26
76.49
best: 90 (Linear FT(ViT-L/14))
TransBoost: Improving the Best ImageNet Performance using Deep Transduction arXiv:2205.13331
Image ClassificationonCIFAR-10
Percentage correct· 2022-05-26
97.61
best: 99.5 (ViT-H/14)
TransBoost: Improving the Best ImageNet Performance using Deep Transduction arXiv:2205.13331
Image ClassificationonFood-101
Accuracy (%)· 2022-05-26
84.3
best: 92.9 (Bamboo (ViTB/16))
TransBoost: Improving the Best ImageNet Performance using Deep Transduction arXiv:2205.13331