Junseok, Kang Ahn, Sang Chul 2024-01-19T12:33:39Z 2024-01-19T12:33:39Z 2022-04-05 2022-02 2169-3536 https://pubs.kist.re.kr/handle/201004/115654 In the recent research of Variational Prototyping-Encoder (VPE), the problem of classifying 2D flat objects of the unseen class has been addressed. VPE solves this problem by pre-learning the image translation task from real-world object images to their corresponding prototype images as a meta-task. VPE uses a single prototype for each object class. However, in general, a single prototype is not sufficient to represent a generic object class because the appearance can change significantly according to viewpoints and other factors. In this case, using VPE and a single prototype for each class in training can result in overfitting or performance degradation. One solution may be the use of multiple prototypes. However, this also requires costly sub-labeling for dividing the input class into smaller classes and assigning a prototype to each. Therefore, we propose a new learning method, the variational multi-prototype encoder (VaMPE), which can overcome the limitations of VPE and use multiple prototypes for each object class. The proposed method does not require additional sub-labeling other than simply adding multiple prototypes to each class. Through various experiments, we demonstrate that the proposed method outperforms VPE. English Institute of Electrical and Electronics Engineers Inc. Variational Multi-Prototype Encoder for Object Recognition Using Multiple Prototype Images Article 10.1109/ACCESS.2022.3151856 1 IEEE Access, v.10, pp.19586 - 19598 IEEE Access 10 19586 19598 Y scie scopus 000761186700001 2-s2.0-85124826828 Computer Science, Information Systems Engineering, Electrical & Electronic Telecommunications Computer Science Engineering Telecommunications Article Prototypes Task analysis Training Feature extraction Deep learning Perturbation methods Neural networks Deep learning variational encoder prototype learning embedding space image classification