"Efficient Deep Neural Networks for 3-D Scene Understanding of Unstruct" by Joshua Luke Thompson
In the past decade, deep learning (DL) has taken the world by storm. It has produced significant results in a wide variety of applications ranging from self driving cars to natural language processing (NLP). Modern deep learning is built from a number of different algorithms including artificial neural networks (ANN), optimisation algorithms, back-propagation (BP), and varying levels of supervision. Recent advances in GPU hardware, improved availability of large, high quality datasets, and the d...
Computer Vision Deep Learning Ulti Task Learning Assistive Navigation Semantic Segmentation Monocular Depth Estimation
Source: uow.edu.au