GeminiFusion (MiT-B3)

Reported on 4 benchmarks across 2 tasks · 1 paper

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

Medical2 results

Semantic SegmentationonSUN-RGBD
Mean IoU· 2024-06-03
52.7
best: 54.6 (GeminiFusion (Swin-Large))
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer arXiv:2406.01210
Semantic SegmentationonNYU Depth v2
Mean IoU· 2024-06-03
56.8
best: 63.6 (OmniVec2)
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer arXiv:2406.01210

Audio2 results

10-shot image generationonSUN-RGBD
Mean IoU· 2024-06-03
52.7
best: 54.6 (GeminiFusion (Swin-Large))
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer arXiv:2406.01210
10-shot image generationonNYU Depth v2
Mean IoU· 2024-06-03
56.8
best: 63.6 (OmniVec2)
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer arXiv:2406.01210