2021/06/28 by Mahardhika Pratama, Pratama, Mahardhika, Andri Ashfahani +3 · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Human Pose and Action Recognition #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #cs.AI #cs.LG
paper · pdf · doi:10.48550/arxiv.2106.14563
currently under review
arxiv created 2021/06/28 · openalex publication_date 2021/06/28 · arxiv updated 2021/06/29 · openalex created_date 2022/09/28 · openalex updated_date 2026/07/28
Unsupervised continual learning remains a relatively uncharted territory in the existing literature because the vast majority of existing works call for unlimited access of ground truth incurring expensive labelling cost. Another issue lies in the problem of task boundaries and task IDs which must be known for model's updates or model's predictions hindering feasibility for real-time deployment. Knowledge Retention in Self-Adaptive Deep Continual Learner, (KIERA), is proposed in this paper. KIERA is developed from the notion of flexible deep clustering approach possessing an elastic network structure to cope with changing environments in the timely manner. The centroid-based experience replay is put forward to overcome the catastrophic forgetting problem. KIERA does not exploit any labelled samples for model updates while featuring a task-agnostic merit. The advantage of KIERA has been numerically validated in popular continual learning problems where it shows highly competitive performance compared to state-of-the art approaches. Our implementation is available in \textit\urlhttps://github.com/ContinualAL/KIERA.