Exciting practical applications of scalable deep learning and image recognition in the cloud Georgi Kadrev @georgikadrev Imagga Technologies @imagga GTC’16, April 5th
150+ companies 3,700+ developers all around the world
3Y 150Y 2B+ NEW PHOTOS SHARED EVERY DAY (just to be forgotten in 30 minutes!)
All the buzz words… • Artificial Intelligence • Machine Learning • Deep Learning • DNN • CNN • …
Why not solving the problem using these via an auto-tagging API ?!
As simple as: 1. Submit an image 2. Get list of tags or categories 3. Do whatever you need with them
The tags • physical objects: car, dog, computer, … • scenery and conceptual: office, job, family, … • related terms: car -> vehicle
The categories • personal topics: events, beach, street view, … • safe/unsafe content • or customer defined:
But who would need that… ?
Unsplash: for search • Technologies used: auto-tagging • Impact: reduces/replaces manual tagging, enhances search 10
KIA: for user profiling and advertising • Technologies used: auto-tagging, color extraction • Impact: very precise personalised targeting 11
Tavisca: for sorting out 25M hotel photos • Technologies used: custom auto-categorization • Impact: automates classification, improves browsing experience 12
Seoul National University: for waste sorting • Technologies used: custom auto-categorization • Impact: automates pre-sorting of waste Image source: Wikipedia
Eden: for organizing personal photos http://edenphotos.io
Are we close to human performance? 32.5 % 51.1 % https://demo.algolia.com/clashOfTags/
Thank You! api@imagga.com twitter.com/imagga facebook.com/imagga
Hipster Bar: to let only hipsters in his bar! :)
How we’ve built it? • a lot of image data • precise model optimization • scalable infrastructure
The data challenge and our feedback loop
The specific content challenge and our customer-defined training
The high throughput challenge and on demand infrastructure
Recommend
More recommend
