HVT-S-1

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 ClassificationonImageNet
GFLOPs· 2021-03-19
2.4
best: 1478 (InternImage-H)
Scalable Vision Transformers with Hierarchical Pooling arXiv:2103.10619
Image ClassificationonImageNet-1K (with DeiT-S)
GFLOPs· 2021-03-19
2.7
best: 4.6 (Base (DeiT-S))
Scalable Vision Transformers with Hierarchical Pooling arXiv:2103.10619
Image ClassificationonImageNet-1K (with DeiT-S)
Top 1 Accuracy· 2021-03-19
78.3
best: 80.1 (MCTF ($r=16$))
Scalable Vision Transformers with Hierarchical Pooling arXiv:2103.10619