Next Article in Journal
Comparison of the Blade Element Momentum Theory with Computational Fluid Dynamics for Wind Turbine Simulations in Turbulent Inflow
Previous Article in Journal
Application of RFID to Soil-Erosion Research
Article Menu
Issue 12 (December) cover image

Export Article

Open AccessArticle
Appl. Sci. 2018, 8(12), 2512;

Transfer Incremental Learning Using Data Augmentation

Lab-STICC, IMT Atlantique, 29280 Plouzané, France
Montreal Institute for Learning Algorithms (MILA), Montréal, QC H3C 3J7, Canada
Author to whom correspondence should be addressed.
Received: 22 October 2018 / Revised: 22 November 2018 / Accepted: 28 November 2018 / Published: 6 December 2018
Full-Text   |   PDF [276 KB, uploaded 6 December 2018]   |  


Deep learning-based methods have reached state of the art performances, relying on a large quantity of available data and computational power. Such methods still remain highly inappropriate when facing a major open machine learning problem, which consists of learning incrementally new classes and examples over time. Combining the outstanding performances of Deep Neural Networks (DNNs) with the flexibility of incremental learning techniques is a promising venue of research. In this contribution, we introduce Transfer Incremental Learning using Data Augmentation (TILDA). TILDA is based on pre-trained DNNs as feature extractors, robust selection of feature vectors in subspaces using a nearest-class-mean based technique, majority votes and data augmentation at both the training and the prediction stages. Experiments on challenging vision datasets demonstrate the ability of the proposed method for low complexity incremental learning, while achieving significantly better accuracy than existing incremental counterparts. View Full-Text
Keywords: transfer learning; incremental learning; computer vision transfer learning; incremental learning; computer vision

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Share & Cite This Article

MDPI and ACS Style

Boukli Hacene, G.; Gripon, V.; Farrugia, N.; Arzel, M.; Jezequel, M. Transfer Incremental Learning Using Data Augmentation. Appl. Sci. 2018, 8, 2512.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics



[Return to top]
Appl. Sci. EISSN 2076-3417 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top