Class Incremental Aerial Scene Recognition Under Long-Tailed Distribution

Deep learning excels in aerial scene recognition (ASR) but struggles with learning from sequential data due to catastrophic forgetting. Class incremental learning (CIL) can address this but often assumes a balanced data distribution. Real-world aerial scenes exhibit long-tailed properties, the undesirable bias toward the head classes as well as overfitting for the tail classes aggravate the challenge of class incremental ASR. So here, we introduce a two-stage framework for class incremental ASR under long-tailed distribution. First, the encoder is trained by conventional CIL method. Next, keep the encoder fixed and then distribution transfer via inter-class similarity is used to generate a sufficient number of features for tail classes, thus a more balanced classifier can be trained. Our framework can be easily integrated into existing CIL methods. Experiments on public datasets demonstrated the superior performance of our proposed framework.