Now showing items 1-3 of 3
Deep representation learning on hypersphere
(Georgia Institute of Technology, 2020-07-27)
How to efficiently learn discriminative deep features is arguably one of the core problems in deep learning, since it can benefit a lot of downstream tasks such as visual recognition, object detection, semantic segmentation, ...
Encoding 3D contextual information for dynamic scene understanding
(Georgia Institute of Technology, 2020-04-27)
This thesis aims to demonstrate how using 3D cues improves semantic labeling and object classification. Specifically, we will consider depth, surface normals, object classification, and pixel-wise semantic labeling in this ...
Interactive Scalable Interfaces for Machine Learning Interpretability
(Georgia Institute of Technology, 2020-12-01)
Data-driven paradigms now solve the world's hardest problems by automatically learning from data. Unfortunately, what is learned is often unknown to both the people who train the models and the people they impact. This has ...