Class-Incremental Novel Category Discovery in Remote Sensing Image Scene Classification via Contrastive Learning

Yifan Zhou, Haoran Zhu, Chang Xu, Ruixiang Zhang, Guang Hua, Wen Yang

Abstract

Remote sensing (RS) imagery captures the earth's ever-changing landscapes, reflecting evolving land cover patterns propelled by natural processes and human activities. However, existing RS scene classification methods mainly operate under a closed-set hypothesis, which stumbles when encountering novel emerging scenes. This article addresses the intricate task of RS scene classification without labels for novel scenes under incremental learning, termed class-incremental novel category discovery. We propose a contrastive learning-based novel category discovery pipeline tailored for RS image scene classification, enhancing the ability to learn unlabeled novel class data. Furthermore, within this pipeline, we introduce a positive pair filter to identify more positive sample pairs from novel classes, improving the feature representation capability on unlabeled data. Besides, our contrastive learning pipeline incorporates an old-feature replaying method to alleviate catastrophic forgetting in old classes. Extensive evaluations across three public RS datasets showcase the superiority of our method over state-of-the-art approaches.
BibTeX
@article{zhou2024class,
  author = {Yifan Zhou and Haoran Zhu and Chang Xu and Ruixiang Zhang and Guang Hua and Wen Yang},
  title = {{Class-Incremental Novel Category Discovery in Remote Sensing Image Scene Classification via Contrastive Learning}},
  journal = {IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens.},
  year = {2024},
  url = {https://openreview.net/forum?id=0xdCZtgesh},
}

Loading related content...

Figure