Skip to yearly menu bar Skip to main content


Tutorial

Object-centric Representations in Computer Vision

Yanwei Fu · Francesco Locatello · Tianjun Xiao · Tong He · Ke Fan

Elliott Bay
[ ] [ Project Page ]
Mon 17 Jun 1:30 p.m. PDT — 6 p.m. PDT

Abstract:

This tutorial discusses the evolution of object-centric representation in computer vision and deep learning. Initially inspired by decomposing visual scenes into surfaces and objects, recent developments focus on learning causal variables from high-dimensional observations like images or videos. The tutorial covers the objectives of OCL, its development, and connections with machine learning fields, emphasizing object-centric approaches, especially in unsupervised segmentation. Advances in encoder, decoder, and self-supervised learning objectives are explored, with a focus on real-world applications and challenges. The tutorial also introduces open-source tools and showcases breakthroughs in video-based object-centric learning. This tutorial will have four talks covering the basic ideas, learning good features for object-centric learning, video based object-centric representation, and more diverse real-world applications.

Chat is not available.