当前位置: X-MOL 学术arXiv.cs.CV › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
G2MF-WA: Geometric Multi-Model Fitting with Weakly Annotated Data
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-01-20 , DOI: arxiv-2001.06965
Chao Zhang, Xuequan Lu, Katsuya Hotta, and Xi Yang

In this paper we attempt to address the problem of geometric multi-model fitting with resorting to a few weakly annotated (WA) data points, which has been sparsely studied so far. In weak annotating, most of the manual annotations are supposed to be correct yet inevitably mixed with incorrect ones. The WA data can be naturally obtained in an interactive way for specific tasks, for example, in the case of homography estimation, one can easily annotate points on the same plane/object with a single label by observing the image. Motivated by this, we propose a novel method to make full use of the WA data to boost the multi-model fitting performance. Specifically, a graph for model proposal sampling is first constructed using the WA data, given the prior that the WA data annotated with the same weak label has a high probability of being assigned to the same model. By incorporating this prior knowledge into the calculation of edge probabilities, vertices (i.e., data points) lie on/near the latent model are likely to connect together and further form a subset/cluster for effective proposals generation. With the proposals generated, the $\alpha$-expansion is adopted for labeling, and our method in return updates the proposals. This works in an iterative way. Extensive experiments validate our method and show that the proposed method produces noticeably better results than state-of-the-art techniques in most cases.

中文翻译:

G2MF-WA:具有弱注释数据的几何多模型拟合

在本文中,我们试图通过使用一些弱注释 (WA) 数据点来解决几何多模型拟合问题,到目前为止,这些数据点研究很少。在弱注释中,大部分手动注释都应该是正确的,但不可避免地会混入不正确的注释。WA数据可以通过特定任务的交互方式自然获得,例如,在单应性估计的情况下,可以通过观察图像轻松地用单个标签注释同一平面/对象上的点。受此启发,我们提出了一种新方法来充分利用 WA 数据来提高多模型拟合性能。具体来说,首先使用 WA 数据构建模型建议抽样图,鉴于使用相同弱标签注释的 WA 数据有很高的概率被分配到相同的模型。通过将这种先验知识结合到边缘概率的计算中,潜在模型上/附近的顶点(即数据点)很可能连接在一起并进一步形成一个子集/集群,以有效地生成建议。生成提案后,采用 $\alpha$-expansion 进行标记,我们的方法反过来更新提案。这以迭代方式工作。大量实验验证了我们的方法,并表明在大多数情况下,所提出的方法比最先进的技术产生明显更好的结果。数据点)位于潜在模型上/附近可能会连接在一起并进一步形成一个子集/集群以有效生成建议。生成提案后,采用 $\alpha$-expansion 进行标记,我们的方法反过来更新提案。这以迭代方式工作。大量实验验证了我们的方法,并表明在大多数情况下,所提出的方法比最先进的技术产生明显更好的结果。数据点)位于潜在模型上/附近可能会连接在一起并进一步形成一个子集/集群以有效生成建议。生成提案后,采用 $\alpha$-expansion 进行标记,我们的方法反过来更新提案。这以迭代方式工作。大量实验验证了我们的方法,并表明在大多数情况下,所提出的方法比最先进的技术产生明显更好的结果。
更新日期:2020-01-22
down
wechat
bug