Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2401.11667 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918134533849088 |
|---|---|
| author | Wang, Zhiyuan Qu, Xiaoyang Xiao, Jing Chen, Bokui Wang, Jianzong |
| author_facet | Wang, Zhiyuan Qu, Xiaoyang Xiao, Jing Chen, Bokui Wang, Jianzong |
| contents | This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. INCPrompt's key innovation lies in its use of adaptive key-learner and task-aware prompts that capture task-relevant information. This unique combination encapsulates general knowledge across tasks and encodes task-specific knowledge. Our comprehensive evaluation across multiple continual learning benchmarks demonstrates INCPrompt's superiority over existing algorithms, showing its effectiveness in mitigating catastrophic forgetting while maintaining high performance. These results highlight the significant impact of task-aware incremental prompting on continual learning performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_11667 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | INCPrompt: Task-Aware incremental Prompting for Rehearsal-Free Class-incremental Learning Wang, Zhiyuan Qu, Xiaoyang Xiao, Jing Chen, Bokui Wang, Jianzong Machine Learning This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. INCPrompt's key innovation lies in its use of adaptive key-learner and task-aware prompts that capture task-relevant information. This unique combination encapsulates general knowledge across tasks and encodes task-specific knowledge. Our comprehensive evaluation across multiple continual learning benchmarks demonstrates INCPrompt's superiority over existing algorithms, showing its effectiveness in mitigating catastrophic forgetting while maintaining high performance. These results highlight the significant impact of task-aware incremental prompting on continual learning performance. |
| title | INCPrompt: Task-Aware incremental Prompting for Rehearsal-Free Class-incremental Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2401.11667 |