Transfering Low-Frequency Features for Domain Adaptation
文献类型：会议论文
| 作者 | Li CW(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; Li ZW(李朝闻)
|
| 出版日期 | 2022 |
| 会议日期 | 2022-7-18 至 2022-7-22 |
| 会议地点 | 中国 台北 |
| 英文摘要 | 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. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/51632]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 紫东太初大模型研究中心 |
| 作者单位 | 1.中国科学院大学 2.中国科学院自动化研究所 |
| 推荐引用方式 GB/T 7714 | Li CW,Zhao X,Zhao CY,et al. Transfering Low-Frequency Features for Domain Adaptation[C]. 见:. 中国 台北. 2022-7-18 至 2022-7-22. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。