Open-Category Classification by Adversarial Sample Generation
This addresses the challenge of robust classification in real-world scenarios with incomplete training data, though it appears incremental as it builds on adversarial learning ideas.
The paper tackles the problem of open-category classification, where classifiers must identify unseen classes during prediction, by proposing the ASG framework that uses adversarial learning to generate samples and distinguish seen from unseen categories. Experiments on multiple datasets demonstrate its effectiveness.
In real-world classification tasks, it is difficult to collect training samples from all possible categories of the environment. Therefore, when an instance of an unseen class appears in the prediction stage, a robust classifier should be able to tell that it is from an unseen class, instead of classifying it to be any known category. In this paper, adopting the idea of adversarial learning, we propose the ASG framework for open-category classification. ASG generates positive and negative samples of seen categories in the unsupervised manner via an adversarial learning strategy. With the generated samples, ASG then learns to tell seen from unseen in the supervised manner. Experiments performed on several datasets show the effectiveness of ASG.