Few-shot object detection via baby learning

Author(s)

• Anh-Khoa Nguyen Vu, University of Information Technology
• Nhat-Duy Nguyen, University of Information Technology
• Khanh-Duy Nguyen, University of Information Technology
• Vinh-Tiep Nguyen, University of Information Technology
• Thanh Duc Ngo, University of Information Technology
• Thanh-Toan Do, Monash University
• Tam V. Nguyen, University of DaytonFollow

Document Type

Article

Publication Date

4-1-2022

Publication Source

Image and Vision Computing

Abstract

Few-shot learning is proposed to overcome the problem of scarce training data in novel classes. Recently, few-shot learning has been well adopted in various computer vision tasks such as object recognition and object detection. However, the state-of-the-art (SOTA) methods have less attention to effectively reuse the information from previous stages. In this paper, we propose a new framework of few-shot learning for object detection. In particular, we adopt Baby Learning mechanism along with the multiple receptive fields to effectively utilize the former knowledge in novel domain. The propoed framework imitates the learning process of a baby through visual cues. The extensive experiments demonstrate the superiority of the proposed method over the SOTA methods on the benchmarks (improve average 7.0% on PASCAL VOC and 1.6% on MS COCO).

ISBN/ISSN

0262-8856

Publisher

Elsevier

Volume

120

Keywords

Few-shot object detection, Few-shot learning, Baby learning

eCommons Citation

Vu, Anh-Khoa Nguyen; Nguyen, Nhat-Duy; Nguyen, Khanh-Duy; Nguyen, Vinh-Tiep; Ngo, Thanh Duc; Do, Thanh-Toan; and Nguyen, Tam V., "Few-shot object detection via baby learning" (2022). Computer Science Faculty Publications. 231.
https://ecommons.udayton.edu/cps_fac_pub/231