Few-shot object detection via baby learning
Few-shot object detection via baby learning
复制标题
DOI：
10.1016/j.imavis.2022.104398
复制
发表时间：
2022-02
期刊：
影响因子：
--
通讯作者：
Anh-Khoa Nguyen Vu;Nhat-Duy Nguyen;Khanh-Duy Nguyen;Vinh-Tiep Nguyen;T. Ngo;Thanh-Toan Do;Tam V. Nguyen
中科院分区：
文献类型：
--
作者：
Anh-Khoa Nguyen Vu;Nhat-Duy Nguyen;Khanh-Duy Nguyen;Vinh-Tiep Nguyen;T. Ngo;Thanh-Toan Do;Tam V. Nguyen
提出了少样本学习来克服新类中训练数据不足的问题。近年来，小镜头学习已经被广泛应用于各种计算机视觉任务，如目标识别和目标检测。然而，国家的最先进的（SOTA）的方法有较少的注意，以有效地重用信息，从以前的阶段。在本文中，我们提出了一个新的框架，少镜头学习的目标检测。特别是，我们采用婴儿学习机制沿着与多个感受野，有效地利用在新领域的前知识。该框架通过视觉线索模仿婴儿的学习过程。大量的实验表明，所提出的方法优于SOTA方法的基准（提高平均7.0%的PASCAL VOC和1.6%的MS COCO）。
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).