Computer Science Thesis Oral

  • Remote Access - Zoom
  • Virtual Presentation - ET
  • Ph.D. Student
  • Computer Science Department
  • Carnegie Mellon University
Thesis Orals

Human-efficient Discovery of Edge-based Training Data for Visual Machine Learning

Deep learning enables effective computer vision without hand crafting feature extractors. It has great potential if applied to specialized domains such as ecology, military, and medical science. However, the laborious task of creating \emph{labeled} training sets of rare targets is a major deterrent to achieving its goal. A domain expert's time and attention is precious. We address this problem by designing, implementing, and evaluating Eureka, a system for human-efficient discovery of rare phenomena from unlabeled visual data. Eureka's central idea is interactive content-based search of visual data based on early-discard and machine learning. We first demonstrate its effectiveness for curating training sets of rare objects. By analyzing contributing factors to human efficiency, we identify and evaluate important system-level optimizations that utilize edge computing and intelligent storage. Lastly, we extend Eureka's methodology to the task of discovering temporal events from video data.

Thesis Committee:
Mahadev Satyanarayanan (Chair)
Martial Hebert
Roberta Klatzky
Padmanabhan Pillai (Intel Labs)

Zoom Participation. See announcement.

For More Information, Please Contact: