Open Set Domain Adaptation By Novel Class Discovery
This addresses a domain-specific problem in machine learning for scenarios with unseen target categories, offering an incremental improvement over existing methods.
The paper tackles the problem of Open Set Domain Adaptation (OSDA), where target samples come from categories not present in the source domain, by proposing a method to discover these implicit classes rather than treating them as a single unknown class, achieving state-of-the-art results in OSDA.
In Open Set Domain Adaptation (OSDA), large amounts of target samples are drawn from the implicit categories that never appear in the source domain. Due to the lack of their specific belonging, existing methods indiscriminately regard them as a single class unknown. We challenge this broadly-adopted practice that may arouse unexpected detrimental effects because the decision boundaries between the implicit categories have been fully ignored. Instead, we propose Self-supervised Class-Discovering Adapter (SCDA) that attempts to achieve OSDA by gradually discovering those implicit classes, then incorporating them to restructure the classifier and update the domain-adaptive features iteratively. SCDA performs two alternate steps to achieve implicit class discovery and self-supervised OSDA, respectively. By jointly optimizing for two tasks, SCDA achieves the state-of-the-art in OSDA and shows a competitive performance to unearth the implicit target classes.