Fully Convolutional Networks for Semantic Segmentation (Tadas Danielius, IBM)
Details
Speaker: Tadas Danielius,
Data Scientist and Software Engineer at IBM.
Title: Fully Convolutional Networks for Semantic Segmentation
Abstract:
Recent interest in augmented reality wearables, home-automation devices, and self-driving vehicles has created a strong need for inferring knowledge from imagery. Semantic segmentation is one of the high-level task that paves the way towards complete scene understanding labeling image into semantically meaningful parts and classify each part into one of the pre-determined classes. In this speech the speaker will talk about convolutional neural networks and fully convolutional neural networks (FCNs) for Semantic Segmentation.