Class forge: Boosting feature encoder for few-shot learning with synthesized classes | |
Rui-Qi Wang; Xu-Yao Zhang; Cheng-Lin Liu | |
2021 | |
会议日期 | July 5-9, 2021 |
会议地点 | Shenzhen, China |
英文摘要 | Few-shot Learning (FSL) aims to gain classification ability on novel classes with only a few labeled samples. Previous works explore meta-learning, metric learning, and graph based methods. Though data augmentation is important to enhance the generalizability of neural networks, it is not well exploited in the field of FSL. We investigate the augmentation in FSL and propose Class Forge to synthesize forged classes that help to learn an encoder with better generalization to novel classes. Specifically, Class Forge divides given base visual classes into parts and combines these parts to synthesize forged visual classes. Training with the additional forged classes forces the encoder to learn richer features that can embed different parts, so as to boost the generalization to novel classes. Intrinsically, Class Forge is a "class augmentation" method that provides a simple yet effective way to synthesize classes, other than synthesizing samples of given classes in previous works. Extensive experiments show that Class Forge yields consistent performance gain on different datasets for FSL. And the ablation studies validate that features learned with Class Forge demonstrate better generalization ability. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/47476] |
专题 | 自动化研究所_模式识别国家重点实验室_模式分析与学习团队 |
作者单位 | 中科院自动化所 |
推荐引用方式 GB/T 7714 | Rui-Qi Wang,Xu-Yao Zhang,Cheng-Lin Liu. Class forge: Boosting feature encoder for few-shot learning with synthesized classes[C]. 见:. Shenzhen, China. July 5-9, 2021. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论