{"task":"Semi-Supervised Semantic Segmentation","dataset":"ScribbleKITTI","metric_names":["mIoU (1% Labels)","mIoU (10% Labels)","mIoU (20% Labels)","mIoU (50% Labels)"],"rows":[{"id":37606,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"LaserMix (Voxel)","metrics":{"mIoU (1% Labels)":"44.2","mIoU (10% Labels)":"53.7","mIoU (20% Labels)":"55.1","mIoU (50% Labels)":"56.8"},"paper_url":"https://arxiv.org/abs/2207.00026v4","paper_title":"LaserMix for Semi-Supervised LiDAR Semantic Segmentation","paper_date":"2022-06-30","code_links":[{"title":"ldkong1205/LaserMix","url":"https://github.com/ldkong1205/LaserMix"},{"title":"yuan-zm/dgt-st","url":"https://github.com/yuan-zm/dgt-st"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":37607,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"MeanTeacher (Voxel)","metrics":{"mIoU (1% Labels)":"41.0","mIoU (10% Labels)":"50.1","mIoU (20% Labels)":"52.8","mIoU (50% Labels)":"53.9"},"paper_url":"http://arxiv.org/abs/1703.01780v6","paper_title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","paper_date":"2017-03-06","code_links":[{"title":"CuriousAI/mean-teacher","url":"https://github.com/CuriousAI/mean-teacher"},{"title":"ZHKKKe/PixelSSL","url":"https://github.com/ZHKKKe/PixelSSL"},{"title":"benathi/fastswa-semi-sup","url":"https://github.com/benathi/fastswa-semi-sup"},{"title":"sud0301/semisup-semseg","url":"https://github.com/sud0301/semisup-semseg"},{"title":"liuwei16/ALFNet","url":"https://github.com/liuwei16/ALFNet"},{"title":"Lan1991Xu/ONE_NeurIPS2018","url":"https://github.com/Lan1991Xu/ONE_NeurIPS2018"},{"title":"INK-USC/DualRE","url":"https://github.com/INK-USC/DualRE"},{"title":"shunk031/chainer-MeanTeachers","url":"https://github.com/shunk031/chainer-MeanTeachers"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":37608,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"Sup.-only (Voxel)","metrics":{"mIoU (1% Labels)":"39.2","mIoU (10% Labels)":"48.0","mIoU (20% Labels)":"52.1","mIoU (50% Labels)":"53.8"},"paper_url":"https://arxiv.org/abs/2011.10033v1","paper_title":"Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation","paper_date":"2020-11-19","code_links":[{"title":"xinge008/Cylinder3D","url":"https://github.com/xinge008/Cylinder3D"},{"title":"L-Reichardt/Cylinder3D-updated-CUDA","url":"https://github.com/L-Reichardt/Cylinder3D-updated-CUDA"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":37609,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"LaserMix (Range View)","metrics":{"mIoU (1% Labels)":"38.3","mIoU (10% Labels)":"54.4","mIoU (20% Labels)":"55.6","mIoU (50% Labels)":"58.7"},"paper_url":"https://arxiv.org/abs/2207.00026v4","paper_title":"LaserMix for Semi-Supervised LiDAR Semantic Segmentation","paper_date":"2022-06-30","code_links":[{"title":"ldkong1205/LaserMix","url":"https://github.com/ldkong1205/LaserMix"},{"title":"yuan-zm/dgt-st","url":"https://github.com/yuan-zm/dgt-st"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":37610,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"CutMix-Seg (Range View)","metrics":{"mIoU (1% Labels)":"36.7","mIoU (10% Labels)":"50.7","mIoU (20% Labels)":"52.9","mIoU (50% Labels)":"54.3"},"paper_url":"https://arxiv.org/abs/1906.01916v5","paper_title":"Semi-supervised semantic segmentation needs strong, varied perturbations","paper_date":"2019-06-05","code_links":[{"title":"ZHKKKe/PixelSSL","url":"https://github.com/ZHKKKe/PixelSSL"},{"title":"lorenmt/reco","url":"https://github.com/lorenmt/reco"},{"title":"Britefury/cutmix-semisup-seg","url":"https://github.com/Britefury/cutmix-semisup-seg"},{"title":"moucheng2017/mismatchssl","url":"https://github.com/moucheng2017/mismatchssl"},{"title":"moucheng2017/learning_morphological_perturbation_ssl","url":"https://github.com/moucheng2017/learning_morphological_perturbation_ssl"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":37611,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"CBST (Range View)","metrics":{"mIoU (1% Labels)":"35.7","mIoU (10% Labels)":"50.7","mIoU (20% Labels)":"52.7","mIoU (50% Labels)":"54.6"},"paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Yang_Zou_Unsupervised_Domain_Adaptation_ECCV_2018_paper.html","paper_title":"Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training","paper_date":"2018-09-01","code_links":[{"title":"yzou2/CBST","url":"https://github.com/yzou2/CBST"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":37612,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"MeanTeacher (Range View)","metrics":{"mIoU (1% Labels)":"34.2","mIoU (10% Labels)":"49.8","mIoU (20% Labels)":"51.6","mIoU (50% Labels)":"53.3"},"paper_url":"http://arxiv.org/abs/1703.01780v6","paper_title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","paper_date":"2017-03-06","code_links":[{"title":"CuriousAI/mean-teacher","url":"https://github.com/CuriousAI/mean-teacher"},{"title":"ZHKKKe/PixelSSL","url":"https://github.com/ZHKKKe/PixelSSL"},{"title":"benathi/fastswa-semi-sup","url":"https://github.com/benathi/fastswa-semi-sup"},{"title":"sud0301/semisup-semseg","url":"https://github.com/sud0301/semisup-semseg"},{"title":"liuwei16/ALFNet","url":"https://github.com/liuwei16/ALFNet"},{"title":"Lan1991Xu/ONE_NeurIPS2018","url":"https://github.com/Lan1991Xu/ONE_NeurIPS2018"},{"title":"INK-USC/DualRE","url":"https://github.com/INK-USC/DualRE"},{"title":"shunk031/chainer-MeanTeachers","url":"https://github.com/shunk031/chainer-MeanTeachers"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":37613,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"CPS (Range View)","metrics":{"mIoU (1% Labels)":"33.7","mIoU (10% Labels)":"50.0","mIoU (20% Labels)":"52.8","mIoU (50% Labels)":"54.6"},"paper_url":"https://arxiv.org/abs/2106.01226v2","paper_title":"Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision","paper_date":"2021-06-02","code_links":[{"title":"charlesCXK/TorchSemiSeg","url":"https://github.com/charlesCXK/TorchSemiSeg"},{"title":"harshm121/m3l","url":"https://github.com/harshm121/m3l"},{"title":"yhuang1997/3D-CPS","url":"https://github.com/yhuang1997/3D-CPS"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":37614,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"Sup.-only (Range View)","metrics":{"mIoU (1% Labels)":"33.1","mIoU (10% Labels)":"47.7","mIoU (20% Labels)":"49.9","mIoU (50% Labels)":"52.5"},"paper_url":"https://arxiv.org/abs/2109.03787v1","paper_title":"FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding","paper_date":"2021-09-08","code_links":[{"title":"placeforyiming/iros21-fidnet-semantickitti","url":"https://github.com/placeforyiming/iros21-fidnet-semantickitti"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":139351,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"LaserMix (Voxel)","metrics":{"mIoU (1% Labels)":"44.2","mIoU (10% Labels)":"53.7","mIoU (20% Labels)":"55.1","mIoU (50% Labels)":"56.8"},"paper_url":"https://arxiv.org/abs/2207.00026v4","paper_title":"LaserMix for Semi-Supervised LiDAR Semantic Segmentation","paper_date":"2022-06-30","code_links":[{"title":"ldkong1205/LaserMix","url":"https://github.com/ldkong1205/LaserMix"},{"title":"yuan-zm/dgt-st","url":"https://github.com/yuan-zm/dgt-st"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":139352,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"MeanTeacher (Voxel)","metrics":{"mIoU (1% Labels)":"41.0","mIoU (10% Labels)":"50.1","mIoU (20% Labels)":"52.8","mIoU (50% Labels)":"53.9"},"paper_url":"http://arxiv.org/abs/1703.01780v6","paper_title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","paper_date":"2017-03-06","code_links":[{"title":"CuriousAI/mean-teacher","url":"https://github.com/CuriousAI/mean-teacher"},{"title":"ZHKKKe/PixelSSL","url":"https://github.com/ZHKKKe/PixelSSL"},{"title":"benathi/fastswa-semi-sup","url":"https://github.com/benathi/fastswa-semi-sup"},{"title":"sud0301/semisup-semseg","url":"https://github.com/sud0301/semisup-semseg"},{"title":"liuwei16/ALFNet","url":"https://github.com/liuwei16/ALFNet"},{"title":"Lan1991Xu/ONE_NeurIPS2018","url":"https://github.com/Lan1991Xu/ONE_NeurIPS2018"},{"title":"INK-USC/DualRE","url":"https://github.com/INK-USC/DualRE"},{"title":"shunk031/chainer-MeanTeachers","url":"https://github.com/shunk031/chainer-MeanTeachers"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":139353,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"Sup.-only (Voxel)","metrics":{"mIoU (1% Labels)":"39.2","mIoU (10% Labels)":"48.0","mIoU (20% Labels)":"52.1","mIoU (50% Labels)":"53.8"},"paper_url":"https://arxiv.org/abs/2011.10033v1","paper_title":"Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation","paper_date":"2020-11-19","code_links":[{"title":"xinge008/Cylinder3D","url":"https://github.com/xinge008/Cylinder3D"},{"title":"L-Reichardt/Cylinder3D-updated-CUDA","url":"https://github.com/L-Reichardt/Cylinder3D-updated-CUDA"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":139354,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"LaserMix (Range View)","metrics":{"mIoU (1% Labels)":"38.3","mIoU (10% Labels)":"54.4","mIoU (20% Labels)":"55.6","mIoU (50% Labels)":"58.7"},"paper_url":"https://arxiv.org/abs/2207.00026v4","paper_title":"LaserMix for Semi-Supervised LiDAR Semantic Segmentation","paper_date":"2022-06-30","code_links":[{"title":"ldkong1205/LaserMix","url":"https://github.com/ldkong1205/LaserMix"},{"title":"yuan-zm/dgt-st","url":"https://github.com/yuan-zm/dgt-st"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":139355,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"CutMix-Seg (Range View)","metrics":{"mIoU (1% Labels)":"36.7","mIoU (10% Labels)":"50.7","mIoU (20% Labels)":"52.9","mIoU (50% Labels)":"54.3"},"paper_url":"https://arxiv.org/abs/1906.01916v5","paper_title":"Semi-supervised semantic segmentation needs strong, varied perturbations","paper_date":"2019-06-05","code_links":[{"title":"ZHKKKe/PixelSSL","url":"https://github.com/ZHKKKe/PixelSSL"},{"title":"lorenmt/reco","url":"https://github.com/lorenmt/reco"},{"title":"Britefury/cutmix-semisup-seg","url":"https://github.com/Britefury/cutmix-semisup-seg"},{"title":"moucheng2017/mismatchssl","url":"https://github.com/moucheng2017/mismatchssl"},{"title":"moucheng2017/learning_morphological_perturbation_ssl","url":"https://github.com/moucheng2017/learning_morphological_perturbation_ssl"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":139356,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"CBST (Range View)","metrics":{"mIoU (1% Labels)":"35.7","mIoU (10% Labels)":"50.7","mIoU (20% Labels)":"52.7","mIoU (50% Labels)":"54.6"},"paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Yang_Zou_Unsupervised_Domain_Adaptation_ECCV_2018_paper.html","paper_title":"Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training","paper_date":"2018-09-01","code_links":[{"title":"yzou2/CBST","url":"https://github.com/yzou2/CBST"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":139357,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"MeanTeacher (Range View)","metrics":{"mIoU (1% Labels)":"34.2","mIoU (10% Labels)":"49.8","mIoU (20% Labels)":"51.6","mIoU (50% Labels)":"53.3"},"paper_url":"http://arxiv.org/abs/1703.01780v6","paper_title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","paper_date":"2017-03-06","code_links":[{"title":"CuriousAI/mean-teacher","url":"https://github.com/CuriousAI/mean-teacher"},{"title":"ZHKKKe/PixelSSL","url":"https://github.com/ZHKKKe/PixelSSL"},{"title":"benathi/fastswa-semi-sup","url":"https://github.com/benathi/fastswa-semi-sup"},{"title":"sud0301/semisup-semseg","url":"https://github.com/sud0301/semisup-semseg"},{"title":"liuwei16/ALFNet","url":"https://github.com/liuwei16/ALFNet"},{"title":"Lan1991Xu/ONE_NeurIPS2018","url":"https://github.com/Lan1991Xu/ONE_NeurIPS2018"},{"title":"INK-USC/DualRE","url":"https://github.com/INK-USC/DualRE"},{"title":"shunk031/chainer-MeanTeachers","url":"https://github.com/shunk031/chainer-MeanTeachers"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":139358,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"CPS (Range View)","metrics":{"mIoU (1% Labels)":"33.7","mIoU (10% Labels)":"50.0","mIoU (20% Labels)":"52.8","mIoU (50% Labels)":"54.6"},"paper_url":"https://arxiv.org/abs/2106.01226v2","paper_title":"Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision","paper_date":"2021-06-02","code_links":[{"title":"charlesCXK/TorchSemiSeg","url":"https://github.com/charlesCXK/TorchSemiSeg"},{"title":"harshm121/m3l","url":"https://github.com/harshm121/m3l"},{"title":"yhuang1997/3D-CPS","url":"https://github.com/yhuang1997/3D-CPS"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":139359,"task":"Semi-Supervised Semantic Segmentation","parent_task":"Semantic Segmentation","dataset":"ScribbleKITTI","model_name":"Sup.-only (Range View)","metrics":{"mIoU (1% Labels)":"33.1","mIoU (10% Labels)":"47.7","mIoU (20% Labels)":"49.9","mIoU (50% Labels)":"52.5"},"paper_url":"https://arxiv.org/abs/2109.03787v1","paper_title":"FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding","paper_date":"2021-09-08","code_links":[{"title":"placeforyiming/iros21-fidnet-semantickitti","url":"https://github.com/placeforyiming/iros21-fidnet-semantickitti"}],"metrics_order":"[\"mIoU (1% Labels)\", \"mIoU (10% Labels)\", \"mIoU (20% Labels)\", \"mIoU (50% Labels)\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]}]}