Deep visual unsupervised domain adaptation for classification tasks: a survey. Issue 14 (3rd November 2020)

• Record Type: Journal Article
• Authors: Madadi, Yeganeh; Seydi, Vahid; Nasrollahi, Kamal; Hosseini, Reshad; Moeslund, Thomas B.
• Is Part Of: IET image processing. Volume 14:Issue 14(2020)
• Page Start: 3283
• Page End: 3299
• Publication Date: 2020-11-03
• Subjects: unsupervised learning -- computer vision -- image classification; visual unsupervised domain adaptation -- classification tasks -- learning data -- deep unsupervised domain adaptation techniques -- attention‐based methods -- representation‐based methods -- reconstruction‐based methods -- adversarial‐based methods -- discrepancy‐based methods -- computer vision -- taxonomy; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2020.0087
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Learning methods are challenged when there is not enough labelled data. It gets worse when the existing learning data have different distributions in different domains. To deal with such situations, deep unsupervised domain adaptation techniques have newly been widely used. This study surveys such domain adaptation methods that have been used for classification tasks in computer vision. The survey includes the very recent papers on this topic that have not been included in the previous surveys and introduces a taxonomy by grouping methods published on unsupervised domain adaptation into five groups of discrepancy‐, adversarial‐, reconstruction‐, representation‐, and attention‐based methods.