Multivariate Regression on the Grassmannian for Predicting Novel Domains
Multivariate Regression on the Grassmannian for Predicting Novel Domains
复制标题
DOI：
10.1109/cvpr.2016.548
复制
发表时间：
2016-12
期刊：
影响因子：
--
通讯作者：
Yongxin Yang;Timothy M. Hospedales
中科院分区：
文献类型：
--
作者：
Yongxin Yang;Timothy M. Hospedales
我们研究的问题，预测如何识别视觉对象在新的领域既没有标记，也没有未标记的训练数据。领域自适应是一个成熟的研究领域，因为它在改善训练数据和测试数据之间的领域转移问题方面的价值。然而，通常假设域是离散实体，并且在测试域中至少提供未标记的数据。在本文中，我们考虑域由连续值向量参数化的情况（例如，时间、照明或视角）。我们的目标是使用此类领域元数据来预测新的领域以供识别。这允许识别模型预先针对新的域进行预校准（例如，未来时间或视角），而无需等待数据收集和重新训练。我们实现这一点，提出的问题作为一个多元回归的格拉斯曼，在那里我们回归域的子空间（点上的格拉斯曼）对域参数的独立向量。我们得到两个新的方法来实现这一具有挑战性的任务：从RM的直接内核回归！G，以及具有较好外推性能的间接方法。我们在两个跨域视觉识别基准上评估我们的方法，它们的性能接近完整数据域自适应的上限。这表明，数据是不必要的域适应，如果一个域可以参数化描述。
We study the problem of predicting how to recognise visual objects in novel domains with neither labelled nor unlabelled training data. Domain adaptation is now an established research area due to its value in ameliorating the issue of domain shift between train and test data. However, it is conventionally assumed that domains are discrete entities, and that at least unlabelled data is provided in testing domains. In this paper, we consider the case where domains are parametrised by a vector of continuous values (e.g., time, lighting or view angle). We aim to use such domain metadata to predict novel domains for recognition. This allows a recognition model to be pre-calibrated for a new domain in advance (e.g., future time or view angle) without waiting for data collection and re-training. We achieve this by posing the problem as one of multivariate regression on the Grassmannian, where we regress a domain's subspace (point on the Grassmannian) against an independent vector of domain parameters. We derive two novel methodologies to achieve this challenging task: a direct kernel regression from RM ! G, and an indirect method with better extrapolation properties. We evaluate our methods on two crossdomain visual recognition benchmarks, where they perform close to the upper bound of full data domain adaptation. This demonstrates that data is not necessary for domain adaptation if a domain can be parametrically described.