Incremental Open-set Domain Adaptation

TL;DR

This paper introduces IOSDA-Net, a novel approach for incremental open-set domain adaptation in image classification, addressing catastrophic forgetting by generating pseudo source domains and adapting to new target domains without prior domain labels.

Contribution

The paper proposes IOSDA-Net, a two-stage learning pipeline that mitigates catastrophic forgetting in open-set incremental domain adaptation by generating pseudo source domains and adapting to new target domains.

Findings

Effective on Office-Home, DomainNet, and UPRN-RSDA datasets.

Reduces catastrophic forgetting in incremental domain adaptation.

Achieves competitive performance without prior domain labels.

Abstract

Catastrophic forgetting makes neural network models unstable when learning visual domains consecutively. The neural network model drifts to catastrophic forgetting-induced low performance of previously learnt domains when training with new domains. We illuminate this current neural network model weakness and develop a forgetting-resistant incremental learning strategy. Here, we propose a new unsupervised incremental open-set domain adaptation (IOSDA) issue for image classification. Open-set domain adaptation adds complexity to the incremental domain adaptation issue since each target domain has more classes than the Source domain. In IOSDA, the model learns training with domain streams phase by phase in incremented time. Inference uses test data from all target domains without revealing their identities. We proposed IOSDA-Net, a two-stage learning pipeline, to solve the problem. The first module replicates prior domains from random noise using a generative framework and creates a pseudo source domain. In the second step, this pseudo source is adapted to the present target domain. We test our model on Office-Home, DomainNet, and UPRN-RSDA, a newly curated optical remote sensing dataset.