Workshop / Overview

⚠️ A valid COVID certificate must be presented on site to enter the event. ⚠️

  • Item retrieval systems are well implemented in our daily lives, but few are aware of how they are powered.
  • Speaker Identification, Face recognition, Targeted advertisement are all examples of Item retrieval systems.
  • During this workshop we will present what are the mechanisms behind those systems and see how we can implement one of them.
  • We will setup a complete sketch-based image retrieval pipeline, from the processing of the dataset to the deployment of a small web app, including the engineering of the Deep learning model powering it.

Workshop / Outcome

  • Learn how to represent different kinds of data in the same space and align embeddings.
  • Implement a Conditional Variational AutoEncoder and other Deep learning models to create a Sketch-based Image Retrieval system.
  • Create a small web application to expose the sketch-based image retrieval system to a live doodle board."

Workshop / Difficulty

Intermediate level

Workshop / Prerequisites

  • Basic knowledge of python
  • Computer with internet connection

Track / Co-organizers

Gaétan Ramet

Project Manager & Machine Learning Engineer, Visium

Thibault Calvayrac

Machine Learning Engineer, Visium

AMLD EPFL 2021 / Workshops

Towards ethical AI – practical tools for responsible data scientists

With Johan Rochel & Lea Strohm

10:00-11:30 November 10Online

How to make your NLP system multilingual

With Adam Bittlingmayer & Nerses Nersesyan

10:00-12:00 March 02Online

Deep Learning-Driven Text Summarization & Explainability with Reuters News Data

With Nadja Herger, Nina Hristozova & Andreea Iuga

15:00-17:30 March 02Online

AMLD / Global partners