Towards Inheritable Models for Open-Set Domain Adaptation
This addresses a practical limitation in domain adaptation for scenarios like visual recognition where data-sharing is restricted, offering a more feasible approach for real-world applications.
The paper tackles the problem of open-set domain adaptation where target domains contain unseen categories, and existing methods require access to source data, which is impractical due to privacy or proprietary concerns. It introduces a paradigm using source-trained models without source data, achieving state-of-the-art performance in open-set domain adaptation.
There has been a tremendous progress in Domain Adaptation (DA) for visual recognition tasks. Particularly, open-set DA has gained considerable attention wherein the target domain contains additional unseen categories. Existing open-set DA approaches demand access to a labeled source dataset along with unlabeled target instances. However, this reliance on co-existing source and target data is highly impractical in scenarios where data-sharing is restricted due to its proprietary nature or privacy concerns. Addressing this, we introduce a practical DA paradigm where a source-trained model is used to facilitate adaptation in the absence of the source dataset in future. To this end, we formalize knowledge inheritability as a novel concept and propose a simple yet effective solution to realize inheritable models suitable for the above practical paradigm. Further, we present an objective way to quantify inheritability to enable the selection of the most suitable source model for a given target domain, even in the absence of the source data. We provide theoretical insights followed by a thorough empirical evaluation demonstrating state-of-the-art open-set domain adaptation performance.