Language-Mediated, Object-Centric Representation Learning
@article{Wang2020LanguageMediatedOR,
title={Language-Mediated, Object-Centric Representation Learning},
author={Ruocheng Wang and Jiayuan Mao and S. Gershman and Jiajun Wu},
journal={ArXiv},
year={2020},
volume={abs/2012.15814}
}We present Language-mediated, Object-centric Representation Learning (LORL), a paradigm for learning disentangled, object-centric scene representations from vision and language. LORL builds upon recent advances in unsupervised object segmentation, notably MONet and Slot Attention. While these algorithms learn an object-centric representation just by reconstructing the input image, LORL enables them to further learn to associate the learned representations to concepts, i.e., words for object… Expand