Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2603.20292 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918400336330752 |
|---|---|
| author | Zhu, Songfeng |
| author_facet | Zhu, Songfeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_20292 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HSI Image Enhancement Classification Based on Knowledge Distillation: A Study on Forgetting Zhu, Songfeng Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning 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. |
| title | HSI Image Enhancement Classification Based on Knowledge Distillation: A Study on Forgetting |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2603.20292 |