Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation
Sunandini Sanyal, Ashish Ramayee Asokan, Suvaansh Bhambri, Akshay Kulkarni, Jogendra Nath Kundu, R. Venkatesh Babu
Abstract
Conventional Domain Adaptation (DA) methods aim to learn domain-invariant feature representations to improve the target adaptation performance. However, we motivate that domain-specificity is equally important since in-domain trained models hold crucial domain-specific properties that are beneficial for adaptation. Hence, we propose to build a framework that supports disentanglement and learning of domain-specific factors and task-specific factors in a unified model. Motivated by the success of vision transformers in several multi-modal vision problems, we find that queries could be leveraged to extract the domain-specific factors. Hence, we propose a novel Domain-Specificity inducing Transformer (DSiT) framework <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> for disentangling and learning both domain-specific and task-specific factors. To achieve disentanglement, we propose to construct novel Domain-Representative Inputs (DRI) with domain-specific information to train a domain classifier with a novel domain token. We are the first to utilize vision transformers for domain adaptation in a privacy-oriented source-free setting, and our approach achieves state-of-the-art performance on single-source, multi-source, and multi-target benchmarks.