Neural networks encounter the challenge of Catastrophic Forgetting (CF) in continual learning, where new task knowledge interferes with previously learned knowledge. We propose Remembering Transformer, inspired by the brain's Complementary Learning Systems (CLS), to tackle this issue. Remembering Transformer employs a mixture-of-adapters and a generative model-based routing mechanism to alleviate CF by dynamically routing task data to relevant adapters. Our approach demonstrated a new SOTA performance in various vision continual learning tasks and great parameter efficiency.

翻译：神经网络在连续学习中面临灾难性遗忘（CF）的挑战，即新任务知识会干扰已学知识。受大脑互补学习系统（CLS）的启发，我们提出记忆Transformer以解决该问题。记忆Transformer采用混合适配器与基于生成模型的路由机制，通过动态地将任务数据路由至相关适配器来缓解灾难性遗忘。该方法在多种视觉连续学习任务中展现出新的最先进性能，并具有卓越的参数效率。