Multiscale Transformer Encoder

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Computer Vision4 results

Image MatchingonBrown Dataset
FPR95· 2021-03-20
0.9
best: 1.27 (Twin-Net)
SOTA
Attention-Based Multimodal Image Matching arXiv:2103.11247
Image MatchingonVisNir
FPR95· 2021-03-20
1.44
SOTA
Attention-Based Multimodal Image Matching arXiv:2103.11247
Patch MatchingonBrown Dataset
FPR95· 2021-03-20
0.9
best: 1.27 (Twin-Net)
SOTA
Attention-Based Multimodal Image Matching arXiv:2103.11247
Patch MatchingonVisNir
FPR95· 2021-03-20
1.44
SOTA
Attention-Based Multimodal Image Matching arXiv:2103.11247