OpenLORIS-Object : A Robotic Vision Dataset and Benchmark for Lifelong Deep Learning

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

9 Scopus Citations
View graph of relations

Author(s)

  • Xinyue Hao
  • Qihan Yang
  • Vincenzo Lomonaco
  • Xuesong Shi
  • Zhengwei Wang
  • Yao Guo
  • Yimin Zhang
  • Fei Qiao

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publication2020 IEEE International Conference on Robotics and Automation (ICRA)
PublisherIEEE
Pages4767-4773
Number of pages7
ISBN (Electronic)978-1-7281-7395-5
Publication statusPublished - May 2020

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729

Conference

Title2020 IEEE International Conference on Robotics and Automation (ICRA 2020)
LocationVirtual Conference
PlaceFrance
CityParis
Period31 May - 31 August 2020

Abstract

The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses unique challenges for applying visual algorithms developed from these standard computer vision datasets due to their implicit assumption over non-varying distributions for a fixed set of tasks. Fully retraining models each time a new task becomes available is infeasible due to computational, storage and sometimes privacy issues, while naıve incremental strategies have been shown to suffer from catastrophic forgetting. It is crucial for the robots to operate continuously under openset and detrimental conditions with adaptive visual perceptual systems, where lifelong learning is a fundamental capability. However, very few datasets and benchmarks are available to evaluate and compare emerging techniques. To fill this gap, we provide a new lifelong robotic vision dataset (“OpenLORISObject”) collected via RGB-D cameras. The dataset embeds the challenges faced by a robot in the real-life application and provides new benchmarks for validating lifelong object recognition algorithms. Moreover, we have provided a testbed of 9 state-of-the-art lifelong learning algorithms. Each of them involves 48 tasks with 4 evaluation metrics over the OpenLORIS-Object dataset. The results demonstrate that the object recognition task in the ever-changing difficulty environments is far from being solved and the bottlenecks are at the forward/backward transfer designs.

Citation Format(s)

OpenLORIS-Object : A Robotic Vision Dataset and Benchmark for Lifelong Deep Learning. / She, Qi; Feng, Fan; Hao, Xinyue; Yang, Qihan; Lan, Chuanlin; Lomonaco, Vincenzo; Shi, Xuesong; Wang, Zhengwei; Guo, Yao; Zhang, Yimin; Qiao, Fei; Chan, Rosa H. M.

2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2020. p. 4767-4773 9196887 (Proceedings - IEEE International Conference on Robotics and Automation).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review