Lecture

Synthetic Training Data via Generative Models

Description

This lecture explores the benefits of synthetic data in computer vision, focusing on generative models that mimic real images with low sim2real gap. It covers the challenges of generating diverse datasets and improving transfer performance through techniques like Textual Inversion and SDEdit.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Instructor

enim do

Ea anim esse eiusmod voluptate laboris minim ullamco nulla in irure. Tempor qui aliquip occaecat dolor cupidatat magna veniam elit. Reprehenderit ex laborum proident commodo duis ullamco quis nulla dolor proident. Mollit dolor magna ut veniam duis magna cupidatat sit.

Official source

https://mediaspace.epfl.ch/media/0_g9mnt3gl

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related lectures (33)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.