@inproceedings{bd9afb967c164be6a5d0fe5c022935d2,
title = "Cross Domain Image Matching in Presence of Outliers",
abstract = "Cross domain image matching between image collections from different source and target domains is challenging in times of deep learning due to i) limited variation of image conditions in a training set, ii) lack of paired-image labels during training, iii) the existing of outliers that makes image matching domains not fully overlap. To this end, we propose an end-to-end architecture that can match cross domain images without labels in the target domain and handle non-overlapping domains by outlier detection. We leverage domain adaptation and triplet constraints for training a network capable of learning domain invariant and identity distinguishable representations, and iteratively detecting the outliers with an entropy loss and our proposed weighted MK-MMD. Extensive experimental evidence on Office [17] dataset and our proposed datasets Shape, Pitts-CycleGAN shows that the proposed approach yields state-of-the-art cross domain image matching and outlier detection performance on different benchmarks. The code will be made publicly available. ",
keywords = "Domain adaptation, Image matching, Outlier detection",
author = "Xin Liu and Seyran Khademi and {van Gemert}, {Jan C.}",
year = "2019",
doi = "10.1109/ICCVW.2019.00406",
language = "English",
isbn = "978-1-7281-5024-6",
series = "Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019",
pages = "3250--3256",
booktitle = "Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019",
note = "ICCV workshop on Transferring and Adapting Source Knowledge in Computer Vision ; Conference date: 02-11-2019 Through 02-11-2019",
}