Knowledge Commons of Institute of Automation,CAS
Transfering Low-Frequency Features for Domain Adaptation | |
Li ZW(李朝闻)1,2; Zhao X(赵旭)1,2; Zhao CY(赵朝阳)1,2; Tang M(唐明)1,2; Wang JQ(王金桥)1,2 | |
2022 | |
会议名称 | ICME |
会议日期 | 2022-7-18 至 2022-7-22 |
会议地点 | 中国 台北 |
摘要 | Previous unsupervised domain adaptation methods did not handle the cross-domain problem from the perspective of frequency for computer vision. The images or feature maps of different domains can be decomposed into the low-frequency component and high-frequency component. This paper proposes the assumption that low-frequency information is more domain-invariant while the high-frequency information contains domain-related information. Hence, we introduce an approach, named low-frequency module (LFM), to extract
domain-invariant feature representations. The LFM is constructed with the digital Gaussian low-pass filter. Our method is easy to implement and introduces no extra hyperparameter. We design two effective ways to utilize the LFM for domain adaptation, and our method is complementary to other existing methods and formulated as a plug-and-play unit that can be combined with these methods. Experimental results demonstrate that our LFM outperforms state-of-the-art meth
ods for various computer vision tasks, including image classification and object detection. |
收录类别 | EI |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 是 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51632 |
专题 | 紫东太初大模型研究中心_图像与视频分析 紫东太初大模型研究中心 |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li ZW,Zhao X,Zhao CY,et al. Transfering Low-Frequency Features for Domain Adaptation[C],2022. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
ICME_cameraready.pdf(746KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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