Show simple item record

dc.contributor.authorTong, JunYong 14:34:07 (GMT) 14:34:07 (GMT)
dc.description.abstractWith the advancement of computation capability, in particular the use of graphical processing units, deep learning systems have shown tremendous potential in achieving super-human performance in many computer vision tasks. However, deep learning models are not able to learn continuously in scenarios where the data distribution is non-stationary or imbalanced, because the models suffer from catastrophic forgetting. In this thesis, we propose an Incremental Generative Replay Embedding (IGRE) framework which employs a conditional generator for generative replay at the image embedding level, thus combining the superior performance of replay and reducing the memory complexities for replay at the same time. Alternating backpropagation with Langevin's dynamics was used for efficient and effective training of the conditional generator. We evaluate the proposed IGRE framework on common benchmarks using CIFAR10/100, CUB and ImageNet datasets. Results show that the proposed IGRE framework outperforms state-of-the-art methods on CIFAR-10, CIFAR-100, and the CUB datasets with 6-9\% improvement in accuracy and achieves comparable performance in large-scale ImageNet experiments, while at the same time reducing the memory requirements significantly when compared to conventional replay techniques.en
dc.publisherUniversity of Waterlooen
dc.subjectDeep Neural Networksen
dc.subjectContinual Learningen
dc.subjectGenerative Modelsen
dc.titleClass Incremental Learning in Deep Neural Networksen
dc.typeMaster Thesisen
dc.pendingfalse Design Engineeringen Design Engineeringen of Waterlooen
uws-etd.degreeMaster of Applied Scienceen
uws.contributor.advisorFieguth, Paul
uws.contributor.affiliation1Faculty of Engineeringen

Files in this item


This item appears in the following Collection(s)

Show simple item record


University of Waterloo Library
200 University Avenue West
Waterloo, Ontario, Canada N2L 3G1
519 888 4883

All items in UWSpace are protected by copyright, with all rights reserved.

DSpace software

Service outages