Imperial College London
Portrait Picture

DR BERNHARD KAINZ

Faculty of Engineering, Department of Computing

Reader in Medical Image Computing
 
 
 
//

Contact

 

+44 (0)20 7594 8349b.kainz Website CV

 
 
//

Location

 

372Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Meng:2020:10.1007/978-3-030-60334-2_15,
author = {Meng, Q and Rueckert, D and Kainz, B},
doi = {10.1007/978-3-030-60334-2_15},
pages = {146--157},
publisher = {Springer International Publishing},
title = {Unsupervised cross-domain image classification by distance metric guided feature alignment},
url = {http://dx.doi.org/10.1007/978-3-030-60334-2_15},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Learning deep neural networks that are generalizable across different domains remains a challenge due to the problem of domain shift. Unsupervised domain adaptation is a promising avenue which transfers knowledge from a source domain to a target domain without using any labels in the target domain. Contemporary techniques focus on extracting domain-invariant features using domain adversarial training. However, these techniques neglect to learn discriminative class boundaries in the latent representation space on a target domain and yield limited adaptation performance. To address this problem, we propose distance metric guided feature alignment (MetFA) to extract discriminative as well as domain-invariant features on both source and target domains. The proposed MetFA method explicitly and directly learns the latent representation without using domain adversarial training. Our model integrates class distribution alignment to transfer semantic knowledge from a source domain to a target domain. We evaluate the proposed method on fetal ultrasound datasets for cross-device image classification. Experimental results demonstrate that the proposed method outperforms the state-of-the-art and enables model generalization.
AU  - Meng,Q
AU  - Rueckert,D
AU  - Kainz,B
DO  - 10.1007/978-3-030-60334-2_15
EP  - 157
PB  - Springer International Publishing
PY  - 2020///
SN  - 0302-9743
SP  - 146
TI  - Unsupervised cross-domain image classification by distance metric guided feature alignment
UR  - http://dx.doi.org/10.1007/978-3-030-60334-2_15
UR  - http://hdl.handle.net/10044/1/84911
ER  -
Download