Creating Efficient, Flexible, and Scalable Cloud Computer Vision Applications: An Introduction

Wednesday, May 22, 4:55 PM - 5:25 PM
Summit Track: 
Room 203/204

Given the growing utility of computer vision applications, how do we deploy these services in high-traffic production environments? Here we present GumGum’s approach to the infrastructure for serving computer vision models in the cloud. We elaborate on a few aspects. First, modularity of computer vision models, including handling images and video equivalently, creating module pipelines and designing for library agnosticism so we can leverage open source developments. Second, we discuss inter-process communication -- specifically, the pros and cons of data serialization, and the importance of standardized data formats between training and serving data, which lends itself to automated feedback from serving data for re-training and automated metrics. Third,we discuss our approaches to scaling, including a producer/consumer model, scaling triggers and container orchestration. We will illustrate these aspects through examples of image and video processing, and module pipelines.


Greg Chu

Sr. Computer Vision Scientist, GumGum

Greg Chu is a Senior Computer Vision Scientist at GumGum, where he works on both the training and large-scale deployment of object detection, recognition and tracking models. These models are applied within GumGum's products for contextual advertising, dental pathology detection and sports sponsorship analytics. Greg has a background in biomedical physics. In his Ph.D research he developed tumor segmentation models to assess the clinical progression of patients in FDA clinical drug trials.

Nishita Sant

Manager Computer Vision, GumGum

Nishita Sant joined GumGum in 2014 as a Computer Vision Scientist. During this time she has worked on Computer Vision problems such as logo detection, image classification, object detection and Text detection and recognition. These applications have been used to support numerous business efforts including contextual targeting in digital advertising, sports sponsorship evaluation and pathology detection from dental x-rays. In addition to churning out models, she is also involved in developing infrastructure for deploying models on Amazon Web Services. Nishita holds a Bachelor's degree in Instrumentation and Control Engineering from University of Pune and a Master’s degree in Electrical Engineering with a concentration in Signal and Image Processing from the University of Southern California. Prior to joining GumGum, Nishita worked in medical imaging at Children’s Hospital and Mathworks.

See you at the Summit! May 20-23 in Santa Clara, California!
Register today and reserve your hotel room!