Implicit Shape Biased Few-Shot Learning for 3D Object Generalization

Implicit Shape Biased Few-Shot Learning for 3D Object Generalization

2022 IEEE International Conference on Image Processing (ICIP)

10.1109/ICIP46576.2022.9897438

http://dx.doi.org/10.1109/icip46576.2022.9897438

Shitala Prasad, Yiqun Li, Dongyun Lin, Aiyuan Guo

18 October 2022

Prasad, S., Li, Y., Lin, D., & Guo, A. (2022). Implicit Shape Biased Few-Shot Learning for 3D Object Generalization. 2022 IEEE International Conference on Image Processing (ICIP). https://doi.org/10.1109/icip46576.2022.9897438

The current state-of-the-art (SOTA) methods validate the role of shape in object categorization, however, except few, most of them neglect object shape information. Motivated by low-shot learning and increasing synthetic data in vision tasks, we investigated how image-based embedding generalization can be improved by the data itself. We propose a new data augmentation approach for low-shot object generalization regime based on image-only. The proposed method learns a discriminative embedding space using SIFT shape points for 3D objects, such that it’s easier to map images and point clouds into one. Numerous experiments show that the proposed approach is superior to the existing low-shot SOTA methods.

Publisher Copyright

This research / project is supported by the A*STAR - RIE2020 INDUSTRY ALIGNMENT FUND - INDUSTRY COLLABORATION PROJECTS (IAF-ICP)
Grant Reference no. : I2001E0073

© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/18779

2381-8549

Institute for Infocomm Research