CORe50: a New Dataset and Benchmark for Continuous Object Recognition

Vincenzo Lomonaco, Davide Maltoni
; Proceedings of the 1st Annual Conference on Robot Learning, PMLR 78:17-26, 2017.

Abstract

Continuous/Lifelong learning of high-dimensional data streams is a challenging research problem. In fact, fully retraining models each time new data become available is infeasible, due to computational and storage issues, while naïve incremental strategies have been shown to suffer from catastrophic forgetting. In the context of real-world object recognition applications (e.g., robotic vision), where continuous learning is crucial, very few datasets and benchmarks are available to evaluate and compare emerging techniques. In this work we propose a new dataset and benchmark CORe50, specifically designed for continuous object recognition, and introduce baseline approaches for different continuous learning scenarios.

Cite this Paper


BibTeX
@InProceedings{pmlr-v78-lomonaco17a, title = {CORe50: a New Dataset and Benchmark for Continuous Object Recognition}, author = {Vincenzo Lomonaco and Davide Maltoni}, booktitle = {Proceedings of the 1st Annual Conference on Robot Learning}, pages = {17--26}, year = {2017}, editor = {Sergey Levine and Vincent Vanhoucke and Ken Goldberg}, volume = {78}, series = {Proceedings of Machine Learning Research}, month = {13--15 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v78/lomonaco17a/lomonaco17a.pdf}, url = {http://proceedings.mlr.press/v78/lomonaco17a.html}, abstract = {Continuous/Lifelong learning of high-dimensional data streams is a challenging research problem. In fact, fully retraining models each time new data become available is infeasible, due to computational and storage issues, while naïve incremental strategies have been shown to suffer from catastrophic forgetting. In the context of real-world object recognition applications (e.g., robotic vision), where continuous learning is crucial, very few datasets and benchmarks are available to evaluate and compare emerging techniques. In this work we propose a new dataset and benchmark CORe50, specifically designed for continuous object recognition, and introduce baseline approaches for different continuous learning scenarios.} }
Endnote
%0 Conference Paper %T CORe50: a New Dataset and Benchmark for Continuous Object Recognition %A Vincenzo Lomonaco %A Davide Maltoni %B Proceedings of the 1st Annual Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2017 %E Sergey Levine %E Vincent Vanhoucke %E Ken Goldberg %F pmlr-v78-lomonaco17a %I PMLR %J Proceedings of Machine Learning Research %P 17--26 %U http://proceedings.mlr.press %V 78 %W PMLR %X Continuous/Lifelong learning of high-dimensional data streams is a challenging research problem. In fact, fully retraining models each time new data become available is infeasible, due to computational and storage issues, while naïve incremental strategies have been shown to suffer from catastrophic forgetting. In the context of real-world object recognition applications (e.g., robotic vision), where continuous learning is crucial, very few datasets and benchmarks are available to evaluate and compare emerging techniques. In this work we propose a new dataset and benchmark CORe50, specifically designed for continuous object recognition, and introduce baseline approaches for different continuous learning scenarios.
APA
Lomonaco, V. & Maltoni, D.. (2017). CORe50: a New Dataset and Benchmark for Continuous Object Recognition. Proceedings of the 1st Annual Conference on Robot Learning, in PMLR 78:17-26

Related Material