Ambiguity-Guided Learnable Distribution Calibration for Semi-Supervised Few-Shot Class-Incremental Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912511863816192 |
|---|---|
| author | Lyu, Fan Zhao, Linglan Liu, Chengyan Mei, Yinying Zhang, Zhang Zhang, Jian Hu, Fuyuan Wang, Liang |
| author_facet | Lyu, Fan Zhao, Linglan Liu, Chengyan Mei, Yinying Zhang, Zhang Zhang, Jian Hu, Fuyuan Wang, Liang |
| contents | Few-Shot Class-Incremental Learning (FSCIL) focuses on models learning new concepts from limited data while retaining knowledge of previous classes. Recently, many studies have started to leverage unlabeled samples to assist models in learning from few-shot samples, giving rise to the field of Semi-supervised Few-shot Class-Incremental Learning (Semi-FSCIL). However, these studies often assume that the source of unlabeled data is only confined to novel classes of the current session, which presents a narrow perspective and cannot align well with practical scenarios. To better reflect real-world scenarios, we redefine Semi-FSCIL as Generalized Semi-FSCIL (GSemi-FSCIL) by incorporating both base and all the ever-seen novel classes in the unlabeled set. This change in the composition of unlabeled samples poses a new challenge for existing methods, as they struggle to distinguish between unlabeled samples from base and novel classes. To address this issue, we propose an Ambiguity-guided Learnable Distribution Calibration (ALDC) strategy. ALDC dynamically uses abundant base samples to correct biased feature distributions for few-shot novel classes. Experiments on three benchmark datasets show that our method outperforms existing works, setting new state-of-the-art results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23237 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ambiguity-Guided Learnable Distribution Calibration for Semi-Supervised Few-Shot Class-Incremental Learning Lyu, Fan Zhao, Linglan Liu, Chengyan Mei, Yinying Zhang, Zhang Zhang, Jian Hu, Fuyuan Wang, Liang Computer Vision and Pattern Recognition Few-Shot Class-Incremental Learning (FSCIL) focuses on models learning new concepts from limited data while retaining knowledge of previous classes. Recently, many studies have started to leverage unlabeled samples to assist models in learning from few-shot samples, giving rise to the field of Semi-supervised Few-shot Class-Incremental Learning (Semi-FSCIL). However, these studies often assume that the source of unlabeled data is only confined to novel classes of the current session, which presents a narrow perspective and cannot align well with practical scenarios. To better reflect real-world scenarios, we redefine Semi-FSCIL as Generalized Semi-FSCIL (GSemi-FSCIL) by incorporating both base and all the ever-seen novel classes in the unlabeled set. This change in the composition of unlabeled samples poses a new challenge for existing methods, as they struggle to distinguish between unlabeled samples from base and novel classes. To address this issue, we propose an Ambiguity-guided Learnable Distribution Calibration (ALDC) strategy. ALDC dynamically uses abundant base samples to correct biased feature distributions for few-shot novel classes. Experiments on three benchmark datasets show that our method outperforms existing works, setting new state-of-the-art results. |
| title | Ambiguity-Guided Learnable Distribution Calibration for Semi-Supervised Few-Shot Class-Incremental Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.23237 |