Deep visual unsupervised domain adaptation for classification tasks: a survey

Research output: Contribution to journalArticlepeer-review

Standard Standard

Deep visual unsupervised domain adaptation for classification tasks: a survey. / Madadi, Yeganeh; Seydi, Vahid; Nasrollahi, Kamal et al.
In: IET Image Processing, Vol. 14, No. 14, 01.12.2020, p. 3283 – 3299.

Research output: Contribution to journalArticlepeer-review

HarvardHarvard

Madadi, Y, Seydi, V, Nasrollahi, K, Hosseini, R & Moeslund, TB 2020, 'Deep visual unsupervised domain adaptation for classification tasks: a survey', IET Image Processing, vol. 14, no. 14, pp. 3283 – 3299. https://doi.org/10.1049/iet-ipr.2020.0087

APA

Madadi, Y., Seydi, V., Nasrollahi, K., Hosseini, R., & Moeslund, T. B. (2020). Deep visual unsupervised domain adaptation for classification tasks: a survey. IET Image Processing, 14(14), 3283 – 3299. https://doi.org/10.1049/iet-ipr.2020.0087

CBE

Madadi Y, Seydi V, Nasrollahi K, Hosseini R, Moeslund TB. 2020. Deep visual unsupervised domain adaptation for classification tasks: a survey. IET Image Processing. 14(14):3283 – 3299. https://doi.org/10.1049/iet-ipr.2020.0087

MLA

VancouverVancouver

Madadi Y, Seydi V, Nasrollahi K, Hosseini R, Moeslund TB. Deep visual unsupervised domain adaptation for classification tasks: a survey. IET Image Processing. 2020 Dec 1;14(14):3283 – 3299. Epub 2020 Nov 3. doi: 10.1049/iet-ipr.2020.0087

Author

Madadi, Yeganeh ; Seydi, Vahid ; Nasrollahi, Kamal et al. / Deep visual unsupervised domain adaptation for classification tasks: a survey. In: IET Image Processing. 2020 ; Vol. 14, No. 14. pp. 3283 – 3299.

RIS

TY - JOUR

T1 - Deep visual unsupervised domain adaptation for classification tasks: a survey

AU - Madadi, Yeganeh

AU - Seydi, Vahid

AU - Nasrollahi, Kamal

AU - Hosseini, Reshad

AU - Moeslund, Thomas B

PY - 2020/12/1

Y1 - 2020/12/1

N2 - 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.

AB - 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.

U2 - 10.1049/iet-ipr.2020.0087

DO - 10.1049/iet-ipr.2020.0087

M3 - Erthygl

VL - 14

SP - 3283

EP - 3299

JO - IET Image Processing

JF - IET Image Processing

IS - 14

ER -