{"task":"Semantic Segmentation","dataset":"Stanford2D3D - RGBD","metric_names":["mIoU","Pixel Accuracy","mAcc"],"rows":[{"id":36526,"task":"Semantic Segmentation","parent_task":null,"dataset":"Stanford2D3D - RGBD","model_name":"CMX (SegFormer-B4)","metrics":{"Pixel Accuracy":"82.6","mIoU":"62.1"},"paper_url":"https://arxiv.org/abs/2203.04838v5","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","paper_date":"2022-03-09","code_links":[{"title":"huaaaliu/rgbx_semantic_segmentation","url":"https://github.com/huaaaliu/rgbx_semantic_segmentation"}],"metrics_order":"[\"mIoU\", \"Pixel Accuracy\", \"mAcc\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":36527,"task":"Semantic Segmentation","parent_task":null,"dataset":"Stanford2D3D - RGBD","model_name":"CMX (SegFormer-B2)","metrics":{"Pixel Accuracy":"82.3","mIoU":"61.2"},"paper_url":"https://arxiv.org/abs/2203.04838v5","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","paper_date":"2022-03-09","code_links":[{"title":"huaaaliu/rgbx_semantic_segmentation","url":"https://github.com/huaaaliu/rgbx_semantic_segmentation"}],"metrics_order":"[\"mIoU\", \"Pixel Accuracy\", \"mAcc\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":36528,"task":"Semantic Segmentation","parent_task":null,"dataset":"Stanford2D3D - RGBD","model_name":"ShapeConv-101","metrics":{"Pixel Accuracy":"82.7","mAcc":"70.0","mIoU":"60.6"},"paper_url":"https://arxiv.org/abs/2108.10528v1","paper_title":"ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation","paper_date":"2021-08-24","code_links":[{"title":"hanchaoleng/shapeconv","url":"https://github.com/hanchaoleng/shapeconv"}],"metrics_order":"[\"mIoU\", \"Pixel Accuracy\", \"mAcc\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":36529,"task":"Semantic Segmentation","parent_task":null,"dataset":"Stanford2D3D - RGBD","model_name":"Linear Fusion (Segformer B2)","metrics":{"mIoU":"57.16"},"paper_url":"https://arxiv.org/abs/2304.10756v1","paper_title":"Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation","paper_date":"2023-04-21","code_links":[{"title":"harshm121/m3l","url":"https://github.com/harshm121/m3l"}],"metrics_order":"[\"mIoU\", \"Pixel Accuracy\", \"mAcc\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":36530,"task":"Semantic Segmentation","parent_task":null,"dataset":"Stanford2D3D - RGBD","model_name":"MMAF-Net-152","metrics":{"Pixel Accuracy":"76.5","mAcc":"62.3","mIoU":"52.9"},"paper_url":"https://arxiv.org/abs/1912.11691v1","paper_title":"Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images","paper_date":"2019-12-25","code_links":[],"metrics_order":"[\"mIoU\", \"Pixel Accuracy\", \"mAcc\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":36531,"task":"Semantic Segmentation","parent_task":null,"dataset":"Stanford2D3D - RGBD","model_name":"Depth-aware CNN","metrics":{"Pixel Accuracy":"65.4","mAcc":"55.5","mIoU":"39.5"},"paper_url":"http://arxiv.org/abs/1803.06791v1","paper_title":"Depth-aware CNN for RGB-D Segmentation","paper_date":"2018-03-19","code_links":[{"title":"laughtervv/DepthAwareCNN","url":"https://github.com/laughtervv/DepthAwareCNN"},{"title":"iriszero/DepthAwareCNNplus","url":"https://github.com/iriszero/DepthAwareCNNplus"},{"title":"aksh1501/DepthAware_CNN_edit","url":"https://github.com/aksh1501/DepthAware_CNN_edit"},{"title":"virkay/DepthAwareCNN2","url":"https://github.com/virkay/DepthAwareCNN2"}],"metrics_order":"[\"mIoU\", \"Pixel Accuracy\", \"mAcc\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":138271,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"Stanford2D3D - RGBD","model_name":"CMX (SegFormer-B4)","metrics":{"Pixel Accuracy":"82.6","mIoU":"62.1"},"paper_url":"https://arxiv.org/abs/2203.04838v5","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","paper_date":"2022-03-09","code_links":[{"title":"huaaaliu/rgbx_semantic_segmentation","url":"https://github.com/huaaaliu/rgbx_semantic_segmentation"}],"metrics_order":"[\"mIoU\", \"Pixel Accuracy\", \"mAcc\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":138272,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"Stanford2D3D - RGBD","model_name":"CMX (SegFormer-B2)","metrics":{"Pixel Accuracy":"82.3","mIoU":"61.2"},"paper_url":"https://arxiv.org/abs/2203.04838v5","paper_title":"CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers","paper_date":"2022-03-09","code_links":[{"title":"huaaaliu/rgbx_semantic_segmentation","url":"https://github.com/huaaaliu/rgbx_semantic_segmentation"}],"metrics_order":"[\"mIoU\", \"Pixel Accuracy\", \"mAcc\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":138273,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"Stanford2D3D - RGBD","model_name":"ShapeConv-101","metrics":{"Pixel Accuracy":"82.7","mAcc":"70.0","mIoU":"60.6"},"paper_url":"https://arxiv.org/abs/2108.10528v1","paper_title":"ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation","paper_date":"2021-08-24","code_links":[{"title":"hanchaoleng/shapeconv","url":"https://github.com/hanchaoleng/shapeconv"}],"metrics_order":"[\"mIoU\", \"Pixel Accuracy\", \"mAcc\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":138274,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"Stanford2D3D - RGBD","model_name":"Linear Fusion (Segformer B2)","metrics":{"mIoU":"57.16"},"paper_url":"https://arxiv.org/abs/2304.10756v1","paper_title":"Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation","paper_date":"2023-04-21","code_links":[{"title":"harshm121/m3l","url":"https://github.com/harshm121/m3l"}],"metrics_order":"[\"mIoU\", \"Pixel Accuracy\", \"mAcc\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":138275,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"Stanford2D3D - RGBD","model_name":"MMAF-Net-152","metrics":{"Pixel Accuracy":"76.5","mAcc":"62.3","mIoU":"52.9"},"paper_url":"https://arxiv.org/abs/1912.11691v1","paper_title":"Multi-Modal Attention-based Fusion Model for Semantic Segmentation of RGB-Depth Images","paper_date":"2019-12-25","code_links":[],"metrics_order":"[\"mIoU\", \"Pixel Accuracy\", \"mAcc\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":138276,"task":"Semantic Segmentation","parent_task":"10-shot image generation","dataset":"Stanford2D3D - RGBD","model_name":"Depth-aware CNN","metrics":{"Pixel Accuracy":"65.4","mAcc":"55.5","mIoU":"39.5"},"paper_url":"http://arxiv.org/abs/1803.06791v1","paper_title":"Depth-aware CNN for RGB-D Segmentation","paper_date":"2018-03-19","code_links":[{"title":"laughtervv/DepthAwareCNN","url":"https://github.com/laughtervv/DepthAwareCNN"},{"title":"iriszero/DepthAwareCNNplus","url":"https://github.com/iriszero/DepthAwareCNNplus"},{"title":"aksh1501/DepthAware_CNN_edit","url":"https://github.com/aksh1501/DepthAware_CNN_edit"},{"title":"virkay/DepthAwareCNN2","url":"https://github.com/virkay/DepthAwareCNN2"}],"metrics_order":"[\"mIoU\", \"Pixel Accuracy\", \"mAcc\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]}]}