HSI Image Enhancement Classification Based on Knowledge Distillation: A Study on Forgetting

TL;DR

This paper presents a novel knowledge distillation approach for incremental hyperspectral image classification that reduces catastrophic forgetting without relying on old category samples, improving model accuracy.

Contribution

It introduces a teacher-based knowledge retention method and a mask-based partial knowledge distillation algorithm to mitigate forgetting and enhance accuracy in incremental learning.

Findings

Robust performance demonstrated through experiments

Effective mitigation of catastrophic forgetting

Enhanced accuracy without old sample dependence

Abstract

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.