Semantic Segmentation On Llrgbd Synthetic

mIoU

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

比較表

モデル名	mIoU
multimodal-token-fusion-for-vision	64.75
understanding-dark-scenes-by-contrasting	67.77
bi-directional-cross-modality-feature	61.79
understanding-dark-scenes-by-contrasting	68.76
cmx-cross-modal-fusion-for-rgb-x-semantic	66.52
shapeconv-shape-aware-convolutional-layer-for	63.26
understanding-dark-scenes-by-contrasting	64.40
channel-exchanging-networks-for-multimodal	62.15