Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency
Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency
复制标题
DOI：
10.1007/978-3-030-01258-8_9
复制
发表时间：
2017-12
期刊：
影响因子：
--
通讯作者：
Xingyi Zhou;Arjun Karpur;Chuang Gan;Linjie Luo;Qi-Xing Huang
中科院分区：
文献类型：
--
作者：
Xingyi Zhou;Arjun Karpur;Chuang Gan;Linjie Luo;Qi-Xing Huang
本文介绍了一种新的无监督域自适应技术，用于从单个深度扫描或图像中预测三维关键点。我们的关键思想是利用这样一个事实，即从不同的角度对相同或相似的物体的预测应该是一致的。这种视图一致性可以为未标记实例的关键点预测提供有效的正则化。此外，我们引入了一个几何对齐项来正则化目标域中的预测。所得到的损失函数可以通过交替最小化有效地优化。我们证明了我们的方法在真实数据集上的有效性，并给出了实验结果，表明我们的方法优于最先进的通用领域自适应技术。
In this paper, we introduce a novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan or image. Our key idea is to utilize the fact that predictions from different views of the same or similar objects should be consistent with each other. Such view consistency can provide effective regularization for keypoint prediction on unlabeled instances. In addition, we introduce a geometric alignment term to regularize predictions in the target domain. The resulting loss function can be effectively optimized via alternating minimization. We demonstrate the effectiveness of our approach on real datasets and present experimental results showing that our approach is superior to state-of-the-art general-purpose domain adaptation techniques.