Cross Domain Image Matching in Presence of Outliers

TL;DR

This paper introduces an end-to-end deep learning architecture for cross domain image matching that effectively handles outliers and domain differences without requiring labeled data, achieving state-of-the-art results.

Contribution

The authors propose a novel method combining domain adaptation, triplet constraints, and outlier detection techniques for unsupervised cross domain image matching.

Findings

Achieves state-of-the-art performance on Office dataset.

Effective outlier detection with entropy loss and weighted MK-MMD.

Robust cross domain matching across diverse datasets.

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.