Unlocking Prototype Potential: An Efficient Tuning Framework for Few-Shot Class-Incremental Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912879394947072 |
|---|---|
| author | Jiang, Shengqin Feng, Xiaoran Qi, Yuankai Zhang, Haokui Hang, Renlong Liu, Qingshan Yao, Lina Sheng, Quan Z. Yang, Ming-Hsuan |
| author_facet | Jiang, Shengqin Feng, Xiaoran Qi, Yuankai Zhang, Haokui Hang, Renlong Liu, Qingshan Yao, Lina Sheng, Quan Z. Yang, Ming-Hsuan |
| contents | Few-shot class-incremental learning (FSCIL) seeks to continuously learn new classes from very limited samples while preserving previously acquired knowledge. Traditional methods often utilize a frozen pre-trained feature extractor to generate static class prototypes, which suffer from the inherent representation bias of the backbone. While recent prompt-based tuning methods attempt to adapt the backbone via minimal parameter updates, given the constraint of extreme data scarcity, the model's capacity to assimilate novel information and substantively enhance its global discriminative power is inherently limited. In this paper, we propose a novel shift in perspective: freezing the feature extractor while fine-tuning the prototypes. We argue that the primary challenge in FSCIL is not feature acquisition, but rather the optimization of decision regions within a static, high-quality feature space. To this end, we introduce an efficient prototype fine-tuning framework that evolves static centroids into dynamic, learnable components. The framework employs a dual-calibration method consisting of class-specific and task-aware offsets. These components function synergistically to improve the discriminative capacity of prototypes for ongoing incremental classes. Extensive results demonstrate that our method attains superior performance across multiple benchmarks while requiring minimal learnable parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05271 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Unlocking Prototype Potential: An Efficient Tuning Framework for Few-Shot Class-Incremental Learning Jiang, Shengqin Feng, Xiaoran Qi, Yuankai Zhang, Haokui Hang, Renlong Liu, Qingshan Yao, Lina Sheng, Quan Z. Yang, Ming-Hsuan Computer Vision and Pattern Recognition Few-shot class-incremental learning (FSCIL) seeks to continuously learn new classes from very limited samples while preserving previously acquired knowledge. Traditional methods often utilize a frozen pre-trained feature extractor to generate static class prototypes, which suffer from the inherent representation bias of the backbone. While recent prompt-based tuning methods attempt to adapt the backbone via minimal parameter updates, given the constraint of extreme data scarcity, the model's capacity to assimilate novel information and substantively enhance its global discriminative power is inherently limited. In this paper, we propose a novel shift in perspective: freezing the feature extractor while fine-tuning the prototypes. We argue that the primary challenge in FSCIL is not feature acquisition, but rather the optimization of decision regions within a static, high-quality feature space. To this end, we introduce an efficient prototype fine-tuning framework that evolves static centroids into dynamic, learnable components. The framework employs a dual-calibration method consisting of class-specific and task-aware offsets. These components function synergistically to improve the discriminative capacity of prototypes for ongoing incremental classes. Extensive results demonstrate that our method attains superior performance across multiple benchmarks while requiring minimal learnable parameters. |
| title | Unlocking Prototype Potential: An Efficient Tuning Framework for Few-Shot Class-Incremental Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.05271 |