oolworkshop.github.io - Object-Oriented Learning (OOL): Perception, Representation, and Reasoning

home > domains > oolworkshop.github.io

Example domain paragraphs

Objects, and the interactions between them, are the foundations on which our understanding of the world is built [1]. Similarly, abstractions centered around the perception and representation of objects play a key role in building human-like AI, supporting high-level cognitive abilities like causal reasoning, object-centric exploration, and problem solving [2,4,5,6]. Indeed, prior works have shown how relational reasoning and control problems can greatly benefit from having object descriptions [2,7]. Yet, m

In this workshop, we will showcase a variety of approaches in object-oriented learning, with three particular emphases. Our first interest is in learning object representations in an unsupervised manner. Although computer vision has made an enormous amount of progress in learning about objects via supervised methods, we believe that learning about objects with little to no supervision is preferable: it minimizes labeling costs, and also supports adaptive representations that can be changed depending on the

We are glad to announce that the following papers received an "Outstanding Paper Award" following the peer-review process. The award consists of 300 USD, generously provided by our sponsors: Deepmind and Kakaobrain . Learning Affordances in Object-Centric Generative Models , by Yizhe Wu, Sudhanshu Kasewa, Oliver M Groth, Sasha Salter, Li Sun, Oiwi Parker Jones, and Ingmar Posner. Counterfactual Data Augmentation using Locally Factored Dynamics , by Silviu Pitis, Elliot Creager, and Animesh Garg. Learning 3D

Links to oolworkshop.github.io (9)



© example3.com 2024