Continual learning is a process that involves training learning agents to
sequentially master a stream of tasks or classes without revisiting past data.
The challenge lies in leveraging previously acquired knowledge to learn new
tasks efficiently, while avoiding catastrophic forgetting. Existing methods
primarily focus on single domains, restricting their applicability to specific
problems.
In this work, we introduce a novel approach called Cross-Domain Continual
Learning (CDCL) that addresses the limitations of being limited to single
supervised domains. Our method combines inter- and intra-task cross-attention
mechanisms within a compact convolutional network. This integration enables the
model to maintain alignment with features from previous tasks, thereby delaying
the data drift that may occur between tasks, while performing unsupervised
cross-domain (UDA) between related domains. By leveraging an
intra-task-specific pseudo-labeling method, we ensure accurate input pairs for
both labeled and unlabeled samples, enhancing the learning process. To validate
our approach, we conduct extensive experiments on public UDA datasets,
showcasing its positive performance on cross-domain continual learning
challenges. Additionally, our work introduces incremental ideas that contribute
to the advancement of this field.
We make our code and models available to encourage further exploration and
reproduction of our results: https://github.com/Ivsucram/CDCL

本研究提出了一种名为交叉领域连续学习（CDCL）的新方法，在一个紧凑的卷积网络中结合了跨任务关注机制，实现了对先前任务特征的对齐，并在相关领域之间进行了无监督的交叉领域学习（UDA）。通过使用一种任务内特定的伪标签方法，确保了有标签和无标签样本的准确输入对，从而增强了学习过程。本方法在公开的 UDA 数据集上进行了广泛实验，显示出在交叉领域连续学习挑战上的良好性能。此外，本研究提出了增量思想，为该领域的进展做出了贡献。