Representation Calibration and Uncertainty Guidance for Class-Incremental Learning based on Vision Language Model
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_ | 1866908704213827584 |
|---|---|
| author | Tan, Jiantao Ma, Peixian Yu, Tong Zhang, Wentao Wang, Ruixuan |
| author_facet | Tan, Jiantao Ma, Peixian Yu, Tong Zhang, Wentao Wang, Ruixuan |
| contents | Class-incremental learning requires a learning system to continually learn knowledge of new classes and meanwhile try to preserve previously learned knowledge of old classes. As current state-of-the-art methods based on Vision-Language Models (VLMs) still suffer from the issue of differentiating classes across learning tasks. Here a novel VLM-based continual learning framework for image classification is proposed. In this framework, task-specific adapters are added to the pre-trained and frozen image encoder to learn new knowledge, and a novel cross-task representation calibration strategy based on a mixture of light-weight projectors is used to help better separate all learned classes in a unified feature space, alleviating class confusion across tasks. In addition, a novel inference strategy guided by prediction uncertainty is developed to more accurately select the most appropriate image feature for class prediction. Extensive experiments on multiple datasets under various settings demonstrate the superior performance of our method compared to existing ones. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09441 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Representation Calibration and Uncertainty Guidance for Class-Incremental Learning based on Vision Language Model Tan, Jiantao Ma, Peixian Yu, Tong Zhang, Wentao Wang, Ruixuan Computer Vision and Pattern Recognition Artificial Intelligence Class-incremental learning requires a learning system to continually learn knowledge of new classes and meanwhile try to preserve previously learned knowledge of old classes. As current state-of-the-art methods based on Vision-Language Models (VLMs) still suffer from the issue of differentiating classes across learning tasks. Here a novel VLM-based continual learning framework for image classification is proposed. In this framework, task-specific adapters are added to the pre-trained and frozen image encoder to learn new knowledge, and a novel cross-task representation calibration strategy based on a mixture of light-weight projectors is used to help better separate all learned classes in a unified feature space, alleviating class confusion across tasks. In addition, a novel inference strategy guided by prediction uncertainty is developed to more accurately select the most appropriate image feature for class prediction. Extensive experiments on multiple datasets under various settings demonstrate the superior performance of our method compared to existing ones. |
| title | Representation Calibration and Uncertainty Guidance for Class-Incremental Learning based on Vision Language Model |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.09441 |