Enhancing Plasticity for First Session Adaptation Continual Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915378229149696 |
|---|---|
| author | Marouf, Imad Eddine Roy, Subhankar Lathuilière, Stéphane Tartaglione, Enzo |
| author_facet | Marouf, Imad Eddine Roy, Subhankar Lathuilière, Stéphane Tartaglione, Enzo |
| contents | The integration of large pre-trained models (PTMs) into Class-Incremental Learning (CIL) has facilitated the development of computationally efficient strategies such as First-Session Adaptation (FSA), which fine-tunes the model solely on the first task while keeping it frozen for subsequent tasks. Although effective in homogeneous task sequences, these approaches struggle when faced with the heterogeneity of real-world task distributions. We introduce Plasticity-Enhanced Test-Time Adaptation in Class-Incremental Learning (PLASTIC), a method that reinstates plasticity in CIL while preserving model stability. PLASTIC leverages Test-Time Adaptation (TTA) by dynamically fine-tuning LayerNorm parameters on unlabeled test data, enabling adaptability to evolving tasks and improving robustness against data corruption. To prevent TTA-induced model divergence and maintain stable learning across tasks, we introduce a teacher-student distillation framework, ensuring that adaptation remains controlled and generalizable. Extensive experiments across multiple benchmarks demonstrate that PLASTIC consistently outperforms both conventional and state-of-the-art PTM-based CIL approaches, while also exhibiting inherent robustness to data corruptions. Code is available at: https://github.com/IemProg/PLASTIC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_11482 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Enhancing Plasticity for First Session Adaptation Continual Learning Marouf, Imad Eddine Roy, Subhankar Lathuilière, Stéphane Tartaglione, Enzo Computer Vision and Pattern Recognition Artificial Intelligence The integration of large pre-trained models (PTMs) into Class-Incremental Learning (CIL) has facilitated the development of computationally efficient strategies such as First-Session Adaptation (FSA), which fine-tunes the model solely on the first task while keeping it frozen for subsequent tasks. Although effective in homogeneous task sequences, these approaches struggle when faced with the heterogeneity of real-world task distributions. We introduce Plasticity-Enhanced Test-Time Adaptation in Class-Incremental Learning (PLASTIC), a method that reinstates plasticity in CIL while preserving model stability. PLASTIC leverages Test-Time Adaptation (TTA) by dynamically fine-tuning LayerNorm parameters on unlabeled test data, enabling adaptability to evolving tasks and improving robustness against data corruption. To prevent TTA-induced model divergence and maintain stable learning across tasks, we introduce a teacher-student distillation framework, ensuring that adaptation remains controlled and generalizable. Extensive experiments across multiple benchmarks demonstrate that PLASTIC consistently outperforms both conventional and state-of-the-art PTM-based CIL approaches, while also exhibiting inherent robustness to data corruptions. Code is available at: https://github.com/IemProg/PLASTIC. |
| title | Enhancing Plasticity for First Session Adaptation Continual Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2310.11482 |