HSI Image Enhancement Classification Based on Knowledge Distillation: A Study on Forgetting
This work addresses incremental learning challenges for hyperspectral image classification, which is incremental in nature.
The paper tackles catastrophic forgetting in incremental classification of hyperspectral images by proposing a teacher-based knowledge retention method that uses only incremental category samples, without relying on old samples, and introduces a mask-based partial category knowledge distillation algorithm to filter misleading information, achieving robust performance in experiments.
In incremental classification tasks for hyperspectral images, catastrophic forgetting is an unavoidable challenge. While memory recall methods can mitigate this issue, they heavily rely on samples from old categories. This paper proposes a teacher-based knowledge retention method for incremental image classification. It alleviates model forgetting of old category samples by utilizing incremental category samples, without depending on old category samples. Additionally, this paper introduces a mask-based partial category knowledge distillation algorithm. By decoupling knowledge distillation, this approach filters out potentially misleading information that could misguide the student model, thereby enhancing overall accuracy. Comparative and ablation experiments demonstrate the proposed method's robust performance.