GeminiFusion

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.

Medical2 results

Semantic SegmentationonDELIVER
mIoU· 2024-06-03
66.9
best: 67.8 (CAFuser)
SOTA
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer arXiv:2406.01210
Semantic SegmentationonDeLiVER
mIoU· 2024-06-03
66.9
best: 68.6 (CAFuser-CAA)
SOTA
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer arXiv:2406.01210

Audio2 results

10-shot image generationonDELIVER
mIoU· 2024-06-03
66.9
best: 67.8 (CAFuser)
SOTA
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer arXiv:2406.01210
10-shot image generationonDeLiVER
mIoU· 2024-06-03
66.9
best: 68.6 (CAFuser-CAA)
SOTA
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer arXiv:2406.01210