Despite the recent progress in incremental learning, addressing catastrophic forgetting under distributional drift is still an open and important problem. Indeed, while state-of-the-art domain incremental learning (DIL) methods perform satisfactorily within known domains, their performance largely degrades in the presence of novel domains. This limitation hampers their generalizability, and restricts their scalability to more realistic settings where train and test data are drawn from different distributions. To address these limitations, we present a novel DIL approach based on a mixture of prompt-tuned CLIP models (MoP-CLIP), which generalizes the paradigm of S-Prompting to handle both in-distribution and out-of-distribution data at inference. In particular, at the training stage we model the features distribution of every class in each domain, learning individual text and visual prompts to adapt to a given domain. At inference, the learned distributions allow us to identify whether a given test sample belongs to a known domain, selecting the correct prompt for the classification task, or from an unseen domain, leveraging a mixture of the prompt-tuned CLIP models. Our empirical evaluation reveals the poor performance of existing DIL methods under domain shift, and suggests that the proposed MoP-CLIP performs competitively in the standard DIL settings while outperforming state-of-the-art methods in OOD scenarios. These results demonstrate the superiority of MoP-CLIP, offering a robust and general solution to the problem of domain incremental learning.

翻译：尽管增量学习近期取得了进展，但解决分布漂移下的灾难性遗忘仍是一个开放且重要的问题。实际上，虽然最先进的域增量学习（DIL）方法在已知域内表现令人满意，但在出现新域时其性能会大幅下降。这一局限性阻碍了其泛化能力，并限制了其在训练数据和测试数据来自不同分布这一更现实场景中的可扩展性。为解决这些问题，我们提出了一种基于提示调优CLIP模型混合的新型DIL方法（MoP-CLIP），该方法推广了S-Prompting范式，以在推理时同时处理分布内和分布外数据。具体而言，在训练阶段，我们对每个域中每个类别的特征分布进行建模，学习独立的文本和视觉提示以适应特定域。在推理时，学习到的分布使我们能够识别给定测试样本是否属于已知域（从而为分类任务选择正确的提示），还是来自未见过的域（从而利用提示调优CLIP模型的混合）。我们的实验评估揭示了现有DIL方法在域漂移下的性能不佳，并表明所提出的MoP-CLIP在标准DIL设置中具有竞争力的性能，同时在OOD场景中优于最先进的方法。这些结果证明了MoP-CLIP的优越性，为域增量学习问题提供了鲁棒且通用的解决方案。