no code implementations • 4 Oct 2021 • Jiahao Huo, Terence L. Van Zyl
We show that one does not require stored images (exemplars) for incremental learning with similarity learning.
no code implementations • 29 Sep 2021 • Jiahao Huo, Terence L van Zyl
We then investigate the viability of generating “embedding” exemplars from a VAE that can protect base knowledge in the intermediate to output layers of the neural networks.
no code implementations • 10 Jun 2020 • Jiahao Huo, Terence L van Zyl
The contribution of this paper is two-fold: to begin, the experiments have established 3-D Convolutional networks and 2-D LSTMs with the contrastive loss on image sequences do not outperform Google/Inception architecture with contrastive loss in top $n$ rank face retrievals with still images.