Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Transfer Incremental Learning using Data Augmentation
Ghouthi Boukli Hacene, Vincent Gripon, Nicolas Farrugia, Matthieu Arzel, Michel Jezequel
Feb 09, 2018 (modified: Jun 04, 2018)ICLR 2018 Workshop Submissionreaders: everyoneShow Bibtex
Abstract:Due to catastrophic forgetting, deep learning remains highly inappropriate when facing incremental learning of new classes and examples over time. In this contribution, we introduce Transfer Incremental Learning using Data Augmentation (TILDA). TILDA combines transfer learning from a pre-trained Deep Neural Network (DNN) as feature extractor, a Nearest Class Mean (NCM) inspired classifier and majority vote using data augmentation on both training and test vectors. The obtained methodology allows learning new examples or classes on the fly with very limited computational and memory footprints. We perform experiments on challenging vision datasets and obtain performance significantly better than existing incremental counterparts.
Keywords:Computer vision, Deep learning, Supervised Learning, Transfer Learning
TL;DR:Combining NCM-inspired classifiers with quantized outputs of a Deep CNN enables lightweight one shot incremental learning.
Enter your feedback below and we'll get back to you as soon as possible.