Exploiting View-Specific Appearance Similarities Across Classes for Zero-Shot Pose Prediction: A Metric Learning Approach
Alina Kuznetsova (Leibniz University Hannover)
Sung Ju Hwang (UNIST)
Bodo Rosenhahn (Leibniz University Hannover)
Leonid Sigal (Disney Research Pittsburgh)
Association for the Advancement of Artificial Intelligence (AAAI) 2016
February 12, 2016
Viewpoint estimation, especially in case of multiple object classes, remains an important and challenging problem. First, objects under different views undergo extreme appearance variations, often making within class variance larger than between-class variance. Second, obtaining precise ground truth for real-world images, necessary for training supervised viewpoint estimation models, is extremely difficult and time-consuming. As a result, annotated data is often available only for a limited number of classes. Hence it is desirable to share viewpoint information across classes. Additional complexity arises from unaligned pose labels between classes, i.e. a side view of a car might look more like a frontal view of a toaster, than its side view. To address these problems, we propose a metric learning approach for joint class prediction and pose estimation. Our approach allows to circumvent the problem of viewpoint alignment across multiple classes and does not require dense viewpoint labels. Moreover, we show, that the learned metric generalizes to new classes, for which the pose labels are not available, and therefore makes it possible to use only partially annotated training sets, relying on the intrinsic similarities in the viewpoint manifolds. We evaluate our approach on two challenging multi-class datasets, 3DObjects, and PASCAL3D+.
Download File "Exploiting View-Specific Appearance Similarities Across Classes for Zero-Shot Pose Prediction- A Metric Learning Approach-Paper"
[pdf, 5.46 MB]