HOpenCls: Training Hyperspectral Image Open-Set Classifiers in Their Living Environments
This addresses the challenge of deploying hyperspectral image classifiers in real-world environments where unknown classes must be rejected, but it is incremental as it builds on existing positive-unlabeled learning methods.
The paper tackles the problem of hyperspectral image open-set classification by proposing HOpenCls, a framework that uses unlabeled wild data to improve performance without requiring annotated auxiliary unknown classes, achieving significant enhancements in complex real-world scenarios.
Hyperspectral image (HSI) open-set classification is critical for HSI classification models deployed in real-world environments, where classifiers must simultaneously classify known classes and reject unknown classes. Recent methods utilize auxiliary unknown classes data to improve classification performance. However, the auxiliary unknown classes data is strongly assumed to be completely separable from known classes and requires labor-intensive annotation. To address this limitation, this paper proposes a novel framework, HOpenCls, to leverage the unlabeled wild data-that is the mixture of known and unknown classes. Such wild data is abundant and can be collected freely during deploying classifiers in their living environments. The key insight is reformulating the open-set HSI classification with unlabeled wild data as a positive-unlabeled (PU) learning problem. Specifically, the multi-label strategy is introduced to bridge the PU learning and open-set HSI classification, and then the proposed gradient contraction and gradient expansion module to make this PU learning problem tractable from the observation of abnormal gradient weights associated with wild data. Extensive experiment results demonstrate that incorporating wild data has the potential to significantly enhance open-set HSI classification in complex real-world scenarios.