*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Image Retrieval and Geolocalization with Deep Learning
Nam Vo
Ph.D. Student
School of Interactive Computing
College of Computing
Georgia Institute of Technology
Date: Tuesday, Dec 11th, 2018
Time: 10:00 AM to 12:00PM (EST)
Location: TBA, College of Computing Building
Committee:
---------------
Dr. James Hays (Advisor), School of Interactive Computing, Georgia Institute of Technology
Dr. Irfan Essa, School of Interactive Computing, Georgia Institute of Technology
Dr. James Rehg, School of Interactive Computing, Georgia Institute of Technology
Dr. Nathan Jacobs, Department of Computer Science, University of Kentucky
Dr. Aaron Bobick, School of Engineering and Applied Science, Washington University in St. Louis
Summary:
---------------
In this thesis, I study image localization task and explore image ranking/retrieval approach. Deep Learning has advanced many computer vision task including image retrieval; in addition, location tagged image data has become increasingly abundant.
Our first contribution is a study of image geolocalization at planet scale (Im2GPS: predicting GPS coordinate from image data) comparing 2 deep learning approaches: image classification and image retrieval. We analyze the trade off between localization accuracy at different granularity levels. Image retrieval approach has great advantage when it comes to geolocalization at fine levels (street, city) and still competitive at coarse levels (country, continent).
Next, we investigate different architectures for matching and retrieving crossview images. The application is to do localization using image retrieval approach where the query images are normal streetview images, but reference images in the database are overhead viewpoint (satellite images).
Our third contribution is exploring state of the art Deep Metric Learning (DML) techniques in image retrieval. We first look at it in the context of fine grained image retrieval, which is much well studied in the literature, and analyze generalization performance when switching embedding layer. Lastly, we apply DML techniques to training deep networks for image retrieval and Im2GPS geolocalization task. Our experiment shows that DML trained systems outperform a classification trained system as feature extractors, result in better image retrieval and geolocalization performance.
