Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination, and environmental changes typically lead to severe degradation in performance. To cope with this problem, recent works have been proposed to adopt domain adaptation techniques. While effective, these methods assume that some prior information about the scenario where the robot will operate is available at training time. Unfortunately, in many cases, this assumption does not hold, as we often do not know where a robot will be deployed. To overcome this issue, in this paper, we present an approach that aims at learning classification models able to generalize to unseen scenarios. Specifically, we propose a novel deep learning framework for domain generalization. Our method develops from the intuition that, given a set of different classification models associated to known domains (e.g., corresponding to multiple environments, robots), the best model for a new sample in the novel domain can be computed directly at test time by optimally combining the known models. To implement our idea, we exploit recent advances in deep domain adaptation and design a convolutional neural network architecture with novel layers performing a weighted version of batch normalization. Our experiments, conducted on three common datasets for robot place categorization, confirm the validity of our contribution.

Robust Place Categorization with Deep Domain Generalization / Mancini, M.; Bulo, S. R.; Caputo, B.; Ricci, E.. - In: IEEE ROBOTICS AND AUTOMATION LETTERS. - ISSN 2377-3766. - 3:3(2018), pp. 2093-2100. [10.1109/LRA.2018.2809700]

Robust Place Categorization with Deep Domain Generalization

Mancini M.;Ricci E.
2018-01-01

Abstract

Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination, and environmental changes typically lead to severe degradation in performance. To cope with this problem, recent works have been proposed to adopt domain adaptation techniques. While effective, these methods assume that some prior information about the scenario where the robot will operate is available at training time. Unfortunately, in many cases, this assumption does not hold, as we often do not know where a robot will be deployed. To overcome this issue, in this paper, we present an approach that aims at learning classification models able to generalize to unseen scenarios. Specifically, we propose a novel deep learning framework for domain generalization. Our method develops from the intuition that, given a set of different classification models associated to known domains (e.g., corresponding to multiple environments, robots), the best model for a new sample in the novel domain can be computed directly at test time by optimally combining the known models. To implement our idea, we exploit recent advances in deep domain adaptation and design a convolutional neural network architecture with novel layers performing a weighted version of batch normalization. Our experiments, conducted on three common datasets for robot place categorization, confirm the validity of our contribution.
2018
3
Mancini, M.; Bulo, S. R.; Caputo, B.; Ricci, E.
Robust Place Categorization with Deep Domain Generalization / Mancini, M.; Bulo, S. R.; Caputo, B.; Ricci, E.. - In: IEEE ROBOTICS AND AUTOMATION LETTERS. - ISSN 2377-3766. - 3:3(2018), pp. 2093-2100. [10.1109/LRA.2018.2809700]
File in questo prodotto:
File Dimensione Formato  
08302933.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 601.84 kB
Formato Adobe PDF
601.84 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/298404
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 39
  • ???jsp.display-item.citation.isi??? ND
social impact