Cross Domain Image Matching in Presence of Outliers
arXiv:1909.03552
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.
arXiv commentICCV Workshop on Transferring and Adaptive Source Knowledge in Computer Vision (TASK-CV) 2019
References in corpus (7)
- How transferable are features in deep neural networks?
- Learning Transferable Features with Deep Adaptation Networks
- Unsupervised Domain Adaptation with Residual Transfer Networks
- Asymmetric Tri-training for Unsupervised Domain Adaptation
- Anomaly Detection using One-Class Neural Networks
- Deep Transfer Network: Unsupervised Domain Adaptation
- Cross-Domain Image Matching with Deep Feature Maps