Documents

DOI

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.
Original languageEnglish
Title of host publicationCCV workshop on Transferring and Adapting Source Knowledge in Computer Vision
Pages3250-3256
Number of pages7
ISBN (Electronic)978-1-7281-5023-9
DOIs
Publication statusPublished - 2019
EventICCV workshop on Transferring and Adapting Source Knowledge in Computer Vision - Seoul, Korea, Democratic People's Republic of
Duration: 2 Nov 20192 Nov 2019

Conference

ConferenceICCV workshop on Transferring and Adapting Source Knowledge in Computer Vision
CountryKorea, Democratic People's Republic of
CitySeoul
Period2/11/192/11/19

ID: 68855622