Learning Factorized Representations for Open-set Domain Adaptation
This addresses the realistic scenario in visual recognition where target domains contain new classes, improving robustness for applications like autonomous driving or surveillance.
The paper tackles open-set domain adaptation, where target data includes unknown classes, by proposing a framework that factorizes data into shared and private subspaces to detect and discard unknown samples, achieving significant outperformance over state-of-the-art methods on standard benchmarks.
Domain adaptation for visual recognition has undergone great progress in the past few years. Nevertheless, most existing methods work in the so-called closed-set scenario, assuming that the classes depicted by the target images are exactly the same as those of the source domain. In this paper, we tackle the more challenging, yet more realistic case of open-set domain adaptation, where new, unknown classes can be present in the target data. While, in the unsupervised scenario, one cannot expect to be able to identify each specific new class, we aim to automatically detect which samples belong to these new classes and discard them from the recognition process. To this end, we rely on the intuition that the source and target samples depicting the known classes can be generated by a shared subspace, whereas the target samples from unknown classes come from a different, private subspace. We therefore introduce a framework that factorizes the data into shared and private parts, while encouraging the shared representation to be discriminative. Our experiments on standard benchmarks evidence that our approach significantly outperforms the state-of-the-art in open-set domain adaptation.