计算机科学
人工智能
机器学习
水准点(测量)
无监督学习
聚类分析
班级(哲学)
任务(项目管理)
再培训
国际贸易
业务
经济
地理
大地测量学
管理
作者
Jiangpeng He,Fengqing Zhu
出处
期刊:Cornell University - arXiv
日期:2021-04-14
被引量:1
标识
DOI:10.48550/arxiv.2104.07164
摘要
Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. However, existing approaches are designed in supervised fashion assuming all data from new tasks have been manually annotated, which are not practical for many real-life applications. In this work, we propose to use pseudo label instead of the ground truth to make continual learning feasible in unsupervised mode. The pseudo labels of new data are obtained by applying global clustering algorithm and we propose to use the model updated from last incremental step as the feature extractor. Due to the scarcity of existing work, we introduce a new benchmark experimental protocol for unsupervised continual learning of image classification task under class-incremental setting where no class label is provided for each incremental learning step. Our method is evaluated on the CIFAR-100 and ImageNet (ILSVRC) datasets by incorporating the pseudo label with various existing supervised approaches and show promising results in unsupervised scenario.
科研通智能强力驱动
Strongly Powered by AbleSci AI