ReMix: Towards Image-to-Image Translation with Limited Data | |
Cao, Jie1,3; Hou, Luanxuan1,3; Yang, Ming-Hsuan2; He, Ran1,3; Sun, Zhenan1,3 | |
2021 | |
会议日期 | 2021年6月19日 – 2021年6月25日 |
会议地点 | 美国田纳西州纳什维尔 |
英文摘要 | Image-to-image (I2I) translation methods based on generative adversarial networks (GANs) typically suffer from overfitting when limited training data is available. In this work, we propose a data augmentation method (ReMix) to tackle this issue. We interpolate training samples at the feature level and propose a novel content loss based on the perceptual relations among samples. The generator learns to translate the in-between samples rather than memorizing the training set, and thereby forces the discriminator to generalize. The proposed approach effectively reduces the ambiguity of generation and renders content-preserving results. The ReMix method can be easily incorporated into existing GAN models with minor modifications. Experimental results on numerous tasks demonstrate that GAN models equipped with the ReMix method achieve significant improvements. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44726] |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | He, Ran |
作者单位 | 1.中国科学院大学 2.加州大学默塞德分校 3.智能感知与计算研究中心 |
推荐引用方式 GB/T 7714 | Cao, Jie,Hou, Luanxuan,Yang, Ming-Hsuan,et al. ReMix: Towards Image-to-Image Translation with Limited Data[C]. 见:. 美国田纳西州纳什维尔. 2021年6月19日 – 2021年6月25日. |
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