Humans and animals have the ability to continuously learn new information over their lifetime without losing previously acquired knowledge. However, artificial neural networks struggle with this due to new information conflicting with old knowledge, resulting in catastrophic forgetting. The complementary learning systems (CLS) theory suggests that the interplay between hippocampus and neocortex systems enables long-term and efficient learning in the mammalian brain, with memory replay facilitating the interaction between these two systems to reduce forgetting. The proposed Lifelong Self-Supervised Domain Adaptation (LLEDA) framework draws inspiration from the CLS theory and mimics the interaction between two networks: a DA network inspired by the hippocampus that quickly adjusts to changes in data distribution and an SSL network inspired by the neocortex that gradually learns domain-agnostic general representations. LLEDA's latent replay technique facilitates communication between these two networks by reactivating and replaying the past memory latent representations to stabilise long-term generalisation and retention without interfering with the previously learned information. Extensive experiments demonstrate that the proposed method outperforms several other methods resulting in a long-term adaptation while being less prone to catastrophic forgetting when transferred to new domains.

翻译：人类和动物具有在终身持续学习新信息而不遗忘先前获得知识的能力。然而，人工神经网络在此方面存在困难，因为新信息与旧知识相冲突，导致灾难性遗忘。互补学习系统（CLS）理论指出，海马体与新皮层系统之间的相互作用使哺乳动物大脑能够实现长期高效学习，记忆回放促进了这两个系统之间的交互，从而减少遗忘。本文提出的终身自监督域自适应（LLEDA）框架受CLS理论启发，模拟了两个网络之间的交互：一个受海马体启发的域自适应网络（DA网络）能够快速适应数据分布变化，另一个受新皮层启发的自监督学习网络（SSL网络）则逐步学习与域无关的通用表征。LLEDA的潜在表示回放技术通过重新激活并回放过去的记忆潜在表征，促进这两个网络之间的通信，从而在不干扰先前学习信息的前提下稳定长期泛化与记忆保持。大量实验表明，所提方法在迁移至新领域时优于多种其他方法，在实现长期适应的同时，显著降低了灾难性遗忘的风险。