Few-shot class-incremental learning (FSCIL) presents a core challenge in continual learning, requiring models to rapidly adapt to new classes with very limited samples while mitigating catastrophic forgetting. Recent prompt-based methods, which integrate pretrained backbones with task-specific prompts, have made notable progress. However, under extreme few-shot incremental settings, the model's ability to transfer and generalize becomes critical, and it is thus essential to leverage pretrained knowledge to learn feature representations that can be shared across future categories during the base session. Inspired by the mechanism of the CLS token, which is similar to human attention and progressively filters out task-irrelevant information, we propose the CLS Token Attention Steering Prompts (CASP). This approach introduces class-shared trainable bias parameters into the query, key, and value projections of the CLS token to explicitly modulate the self-attention weights. To further enhance generalization, we also design an attention perturbation strategy and perform Manifold Token Mixup in the shallow feature space, synthesizing potential new class features to improve generalization and reserve the representation capacity for upcoming tasks. Experiments on the CUB200, CIFAR100, and ImageNet-R datasets demonstrate that CASP outperforms state-of-the-art methods in both standard and fine-grained FSCIL settings without requiring fine-tuning during incremental phases and while significantly reducing the parameter overhead.

翻译：少样本类增量学习（FSCIL）是持续学习中的核心挑战，要求模型在样本极其有限的情况下快速适应新类别，同时缓解灾难性遗忘。近年来，基于提示的方法将预训练主干网络与任务特定提示相结合，取得了显著进展。然而，在极端少样本增量设置下，模型的迁移与泛化能力变得至关重要，因此必须在基础训练阶段有效利用预训练知识，学习能够为未来类别共享的特征表示。受CLS令牌工作机制的启发——该机制类似于人类注意力，能逐步过滤任务无关信息——我们提出了CLS令牌注意力引导提示（CASP）。该方法通过在CLS令牌的查询、键和值投影中引入类别共享的可训练偏置参数，显式调节自注意力权重。为进一步增强泛化能力，我们还设计了注意力扰动策略，并在浅层特征空间执行流形令牌混合，通过合成潜在的新类别特征来提升泛化性能，并为后续任务保留表征容量。在CUB200、CIFAR100和ImageNet-R数据集上的实验表明，CASP在标准与细粒度FSCIL设置中均优于现有先进方法，且无需在增量阶段进行微调，同时显著降低了参数量开销。