中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Learning Domain Invariant Features for Unsupervised Indoor Depth Estimation Adaptation

文献类型：期刊论文

作者Zhang, Jiehua2; Li, Liang3; Yan, Chenggang4; Wang, Zhan5; Xu, Changliang6,7; Zhang, Jiyong4; Chen, Chuqiao1
刊名ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
出版日期2024-09-01
卷号20期号:9页码:23
关键词Indoor depth estimation unsupervised learning transfer learning domain adaptation
ISSN号1551-6857
DOI10.1145/3672397
英文摘要Predicting depth maps from monocular images has made an impressive performance in the past years. However, most depth estimation methods are trained with paired image-depth map data or multi-view images (e.g., stereo pair and monocular sequence), which suffer from expensive annotation costs and poor transferability. Although unsupervised domain adaptation methods are introduced to mitigate the reliance on annotated data, rare works focus on the unsupervised cross-scenario indoor monocular depth estimation. In this article, we propose to study the generalization of depth estimation models across different indoor scenarios in an adversarial-based domain adaptation paradigm. Concretely, a domain discriminator is designed for discriminating the representation from source and target domains, while the feature extractor aims to confuse the domain discriminator by capturing domain-invariant features. Further, we reconstruct depth maps from latent representations with the supervision of labeled source data. As a result, the feature extractor learned features possess the merit of both domain-invariant and low source risk, and the depth estimator can deal with the domain shift between source and target domains. We conduct the cross-scenario and cross-dataset experiments on the ScanNet and NYU-Depth-v2 datasets to verify the effectiveness of our method and achieve impressive performance.
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001325876400003
出版者ASSOC COMPUTING MACHINERY
源URL[http://119.78.100.204/handle/2XEOYT63/39555]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Li, Liang; Yan, Chenggang
作者单位1.Hangzhou Dianzi Univ, Lishui Inst, Hangzhou, Peoples R China
2.Xi An Jiao Tong Univ, Xian, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
4.Hangzhou Dianzi Univ, Hangzhou, Peoples R China
5.Moreal Pte Ltd, Singapore, Singapore
6.State Key Lab Media Convergence Prod Technol Syst, Beijing, Peoples R China
7.Xinhua Zhiyun Technol Co Ltd, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Jiehua,Li, Liang,Yan, Chenggang,et al. Learning Domain Invariant Features for Unsupervised Indoor Depth Estimation Adaptation[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2024,20(9):23.
APA Zhang, Jiehua.,Li, Liang.,Yan, Chenggang.,Wang, Zhan.,Xu, Changliang.,...&Chen, Chuqiao.(2024).Learning Domain Invariant Features for Unsupervised Indoor Depth Estimation Adaptation.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,20(9),23.
MLA Zhang, Jiehua,et al."Learning Domain Invariant Features for Unsupervised Indoor Depth Estimation Adaptation".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 20.9(2024):23.

入库方式： OAI收割

来源：计算技术研究所

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。