Towards lifelong object recognition: A dataset and benchmark

Chuanlin Lan,Fan Feng,Qi Liu,Qi She,Qihan Yang,Xinyue Hao, Ivan Mashkin, Ka Shun Kei,Dong Qiang,Vincenzo Lomonaco,Xuesong Shi,Zhengwei Wang,Yao Guo,Yimin Zhang,Fei Qiao,Rosa H. M. Chan

Pattern Recognition（2022）

引用 2|浏览31

暂无评分

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.

查看译文

关键词

Robotic vision,Continual learning,Lifelong learning,Object recognition

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要