Zhenyu Zhang, Zhen Cui, Chunyan Xu, Yan Yan, N. Sebe, Jian Yang
{"title":"模式亲和传播跨越深度,表面法线和语义分割","authors":"Zhenyu Zhang, Zhen Cui, Chunyan Xu, Yan Yan, N. Sebe, Jian Yang","doi":"10.1109/CVPR.2019.00423","DOIUrl":null,"url":null,"abstract":"In this paper, we propose a novel Pattern-Affinitive Propagation (PAP) framework to jointly predict depth, surface normal and semantic segmentation. The motivation behind it comes from the statistic observation that pattern-affinitive pairs recur much frequently across different tasks as well as within a task. Thus, we can conduct two types of propagations, cross-task propagation and task-specific propagation, to adaptively diffuse those similar patterns. The former integrates cross-task affinity patterns to adapt to each task therein through the calculation on non-local relationships. Next the latter performs an iterative diffusion in the feature space so that the cross-task affinity patterns can be widely-spread within the task. Accordingly, the learning of each task can be regularized and boosted by the complementary task-level affinities. Extensive experiments demonstrate the effectiveness and the superiority of our method on the joint three tasks. Meanwhile, we achieve the state-of-the-art or competitive results on the three related datasets, NYUD-v2, SUN-RGBD and KITTI.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"63 6 1","pages":"4101-4110"},"PeriodicalIF":0.0000,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"209","resultStr":"{\"title\":\"Pattern-Affinitive Propagation Across Depth, Surface Normal and Semantic Segmentation\",\"authors\":\"Zhenyu Zhang, Zhen Cui, Chunyan Xu, Yan Yan, N. Sebe, Jian Yang\",\"doi\":\"10.1109/CVPR.2019.00423\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we propose a novel Pattern-Affinitive Propagation (PAP) framework to jointly predict depth, surface normal and semantic segmentation. The motivation behind it comes from the statistic observation that pattern-affinitive pairs recur much frequently across different tasks as well as within a task. Thus, we can conduct two types of propagations, cross-task propagation and task-specific propagation, to adaptively diffuse those similar patterns. The former integrates cross-task affinity patterns to adapt to each task therein through the calculation on non-local relationships. Next the latter performs an iterative diffusion in the feature space so that the cross-task affinity patterns can be widely-spread within the task. Accordingly, the learning of each task can be regularized and boosted by the complementary task-level affinities. Extensive experiments demonstrate the effectiveness and the superiority of our method on the joint three tasks. Meanwhile, we achieve the state-of-the-art or competitive results on the three related datasets, NYUD-v2, SUN-RGBD and KITTI.\",\"PeriodicalId\":6711,\"journal\":{\"name\":\"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)\",\"volume\":\"63 6 1\",\"pages\":\"4101-4110\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"209\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CVPR.2019.00423\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CVPR.2019.00423","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Pattern-Affinitive Propagation Across Depth, Surface Normal and Semantic Segmentation
In this paper, we propose a novel Pattern-Affinitive Propagation (PAP) framework to jointly predict depth, surface normal and semantic segmentation. The motivation behind it comes from the statistic observation that pattern-affinitive pairs recur much frequently across different tasks as well as within a task. Thus, we can conduct two types of propagations, cross-task propagation and task-specific propagation, to adaptively diffuse those similar patterns. The former integrates cross-task affinity patterns to adapt to each task therein through the calculation on non-local relationships. Next the latter performs an iterative diffusion in the feature space so that the cross-task affinity patterns can be widely-spread within the task. Accordingly, the learning of each task can be regularized and boosted by the complementary task-level affinities. Extensive experiments demonstrate the effectiveness and the superiority of our method on the joint three tasks. Meanwhile, we achieve the state-of-the-art or competitive results on the three related datasets, NYUD-v2, SUN-RGBD and KITTI.