HVT: A Comprehensive Vision Framework for Learning in Non-Euclidean Space

Open paper
Benchmark Model Rank Results
image-classification-on-imagenetHVT Huge#94Top 1 Accuracy: 87.4%
image-classification-on-imagenetHVT Large#264Top 1 Accuracy: 85%
image-classification-on-imagenetHVT Base#684Top 1 Accuracy: 80.1%

Rank counts only results with a code link.