Browsing Theses by Subject "generative adversarial networks"
Now showing items 1-4 of 4
-
Adaptive Fusion Techniques for Effective Multimodal Deep Learning
(University of Waterloo, 2020-08-28)Effective fusion of data from multiple modalities, such as video, speech, and text, is a challenging task due to the heterogeneous nature of multimodal data. In this work, we propose fusion techniques that aim to model ... -
Domain Knowledge Guided Testing and Training of Neural Networks
(University of Waterloo, 2021-08-26)The extensive impact of Deep Neural Networks (DNNs) on various industrial applications and research areas within the last decade can not be overstated. However, they are also subject to notable limitations, namely their ... -
Spectral-Spatial Neural Networks and Probabilistic Graph Models for Hyperspectral Image Classification
(University of Waterloo, 2019-08-16)Pixel-wise hyperspectral image (HSI) classification has been actively studied since it shares similar characteristics with related computer vision tasks, including image classification, object detection, and semantic ... -
Towards Explainable Generative Adversarial Networks
(University of Waterloo, 2022-05-09)As Generative Adversarial Networks become more and more popular for sample generation, the demand for human interpretable explanations have also skyrocketed. With the rising popularity of Generative Adversarial Networks ...