PhD Defense by Nam Vo

Event Details
  • Date/Time:
    • Tuesday December 11, 2018
      10:00 am - 12:00 pm
  • Location: TBA, College of Computing Building
  • Phone:
  • URL:
  • Email:
  • Fee(s):
    N/A
  • Extras:
Contact
No contact information submitted.
Summaries

Summary Sentence: Image Retrieval and Geolocalization with Deep Learning

Full Summary: No summary paragraph submitted.

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.

 

Additional Information

In Campus Calendar
No
Groups

Graduate Studies

Invited Audience
Faculty/Staff, Public, Graduate students, Undergraduate students
Categories
Other/Miscellaneous
Keywords
Phd Defense
Status
  • Created By: Tatianna Richardson
  • Workflow Status: Published
  • Created On: Dec 5, 2018 - 9:42am
  • Last Updated: Dec 5, 2018 - 9:42am