2021/05/27 by Murray Shanahan, Christos Kaplanis, Shanahan, Murray +4
Computer Science · Medicine · #COVID-19 diagnosis using AI #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #cs.LG
paper · pdf · doi:10.48550/arxiv.2105.13327
openalex publication_date 2021/05/27 · arxiv created 2021/10/07 · arxiv updated 2021/10/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We present an architecture that is effective for continual learning in an especially demanding setting, where task boundaries do not exist or are unknown, and where classes have to be learned online (with each example presented only once). To obtain good performance under these constraints, while mitigating catastrophic forgetting, we exploit recent advances in contrastive, self-supervised learning, allowing us to use a pre-trained, general purpose image encoder whose weights can be frozen, which precludes forgetting. The pre-trained encoder also greatly simplifies the downstream task of classification, which we solve with an ensemble of very simple classifiers. Collectively, the ensemble exhibits much better performance than any individual classifier, an effect which is amplified through specialisation and competitive selection. We assess the performance of the encoders-and-ensembles architecture on standard continual learning benchmarks, where it outperforms prior state-of-the-art by a large margin on the hardest problems, as well as in less familiar settings where the data distribution changes gradually or the classes are presented one at a time.