Pose Induction for Novel Object Categories
By Shubham Tulsiani, João Carreira, Jitendra Malik. 2015
35 citations recorded by the source corpus.
We address the task of predicting pose for objects of unannotated object categories from a small seed set of annotated object classes. We present a generalized classifier that can reliably induce pose given a single instance of a novel category. In case of availability of a large collection of novel instances, our approach then jointly reasons over all instances to improve the initial estimates. We empirically validate the various components of our algorithm and quantitatively show that our method produces reliable pose estimates. We also show qualitative results on a diverse set of classes and further demonstrate the applicability of our system for learning shape models of novel object classes.
Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Aerospace Engineering
- Andrea Vedaldi
- Kristen Grauman
- Renaud Marlet
- Yang Xiao
- Qi-Xing Huang
- Subhransu Maji
- Xingyi Zhou
- Dinesh Jayaraman
In Computer Vision and Pattern Recognition
- Andrea Vedaldi
- Luc Van Gool
- Jitendra Malik
- Andrew Zisserman
- Kristen Grauman
- Ming-Hsuan Yang
- Trevor Darrell
- Xiaogang Wang
Citations in the corpus
- 3D Shape Induction from 2D Views of Multiple Objects (2016, methodology): “This may be obtained using a generic view-point estimator such as [30, 28].”
- Learning Image Representations Tied to Egomotion from Unlabeled Video (2017, background): “It has been shown to be possible to predict poses of objects using descriptors learned for classification tasks (Tulsiani et al. 2015).”
- Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild (2020, background): “Most of the existing viewpoint estimation methods are designed for known object categories or instances; very little work reports performance on unseen classes [54, 65, 36, 53, 63].”
- StarMap for Category-Agnostic Keypoint and Viewpoint Estimation (2018, methodology): “For evaluation, they [36] exclude two categories (Motorcycle and Bus) from the Pascal3D+ training set [44] and evaluate viewpoint estimation on these two categories with the same protocol of [37].”
- I Have Seen Enough: Transferring Parts Across Categories (2016, background): “Transferring keypoints was explored in [63], which detects facial landmarks using a deep multi-task learning framework, while [51] induce pose for previously unseen categories.”