Browsing College of Engineering and Informatics by Subject "Data Augmentation"

Now showing items 1-3 of 3

    • Fake data - the future of advanced computer vision systems 

      Corcoran, Peter (NUI Galway, 2018-10-22)
      Recent research shows that Data Augmentation techniques and Synthetic Data can improve the accuracy and reduce the susceptibility of Deep Neural Networks to Adversarial Attacks. In this presentation we consider some of the ...

    • Generative Augmented Dataset and Annotation Frameworks for Artificial Intelligence (GADAFAI) 

      Corcoran, Peter; Javidnia, Hossein; Lemley, Joseph E.; Varkarakis, Viktor (Institute of Electrical and Electronics Engineers (IEEE), 2020-08-31)
      Recent Advances in Artificial Intelligence (AI), particularly in the field of compute vision, have been driven by the availability of large public datasets. However, as AI begins to move into embedded devices there will ...

    • Getting more from your datasets: Data augmentation, annotation and generative techniques 

      Corcoran, Peter; Bazrafkkan, Shabab; Lemley, Joe (XPERI Inc., 2018-05-18)
      Deep Learning for embedded vision requires large datasets. Indeed the more varied training data is, the more accurate the trained network. But, acquiring and accurately annotating datasets costs time and money. This talk ...