Towards lifelong object recognition: A dataset and benchmark

作者：

Highlights：

• We release OpenLORIS-Object, which is the first real-world lifelong learning dataset for robotic vision with quantifiable environmental factors.

• We provide a general benchmark for evaluating lifelong learning capabilities on three continual learning scenarios.

• We analyze 9 SOTA algorithms tested on our dataset, finding that existing algorithms are insufficient to solve the task in a reallifeenvironment.

摘要

•We release OpenLORIS-Object, which is the first real-world lifelong learning dataset for robotic vision with quantifiable environmental factors.•We provide a general benchmark for evaluating lifelong learning capabilities on three continual learning scenarios.•We analyze 9 SOTA algorithms tested on our dataset, finding that existing algorithms are insufficient to solve the task in a reallifeenvironment.

论文关键词：Robotic vision,Continual learning,Lifelong learning,Object recognition

论文评审过程：Received 3 January 2022, Revised 7 May 2022, Accepted 26 May 2022, Available online 27 May 2022, Version of Record 9 June 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108819