Lecture

Synthetic Training Data via Generative Models

Description

This lecture covers the generation of dense annotations with GANs for semantic segmentation, training models on synthetic data, and data augmentation for robot learning. It explores the efficiency of synthetic data, tricks for better performance, and the use of counterfactual image generation for benchmarking.

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

minim aliqua sint nostrud

Non consectetur veniam aute Lorem. Esse deserunt officia officia eu reprehenderit id consectetur consequat irure. Esse culpa est magna quis fugiat nisi pariatur magna incididunt aliqua fugiat ad. Consectetur duis duis consectetur tempor dolore dolor duis duis proident ad. Cupidatat voluptate nulla cillum nisi nulla ullamco veniam tempor nisi proident do qui. Ad voluptate reprehenderit cupidatat esse.

Official source

https://mediaspace.epfl.ch/media/0_qq087w9r

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.

Ontological neighbourhood

Mechanical engineering

Robotics: Topics in robotics

Related lectures (31)

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.