Leveraging over prior knowledge for online learning of visual categories

Tatiana Tommasi, Francesco Orabona, Mohsen Kaboli, Barbara Caputo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Scopus citations


Open ended learning is a dynamic process based on the continuous analysis of new data, guided by past experience. On one side it is helpful to take advantage of prior knowledge when only few information on a new task is available (transfer learning). On the other, it is important to continuously update an existing model so to exploit the new incoming data, especially if their informative content is very different from what is already known (online learning). Until today these two aspects of the learning process have been tackled separately. In this paper we propose an algorithm that takes the best of both worlds: we consider a sequential learning setting, and we exploit the potentiality of knowledge transfer with a computationally cheap solution. At the same time, by relying on past experience we boost online learning to predict reliably on future problems. A theoretical analysis, coupled with extensive experiments, show that our approach performs well in terms of the online number of training mistakes, as well as in terms of performance on separate test sets.
Original languageEnglish (US)
Title of host publicationBMVC 2012 - Electronic Proceedings of the British Machine Vision Conference 2012
PublisherBritish Machine Vision Association, BMVA
StatePublished - Jan 1 2012
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2023-09-25


Dive into the research topics of 'Leveraging over prior knowledge for online learning of visual categories'. Together they form a unique fingerprint.

Cite this