2020/12/31 by Ruocheng Wang, Jiayuan Mao, Wang, Ruocheng +5
Computer Science · Mathematics · #Domain Adaptation and Few-Shot Learning #Human Pose and Action Recognition #Multimodal Machine Learning Applications #cs.CL #cs.CV #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2012.15814
ACL 2021 Findings. First two authors contributed equally; last two authors contributed equally. Project page: https://lang-orl.github.io/
arxiv created 2021/06/08 · arxiv updated 2021/06/09
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 discovery and 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 categories, properties, and spatial relationships, from language input. These object-centric concepts derived from language facilitate the learning of object-centric representations. LORL can be integrated with various unsupervised object discovery algorithms that are language-agnostic. Experiments show that the integration of LORL consistently improves the performance of unsupervised object discovery methods on two datasets via the help of language. We also show that concepts learned by LORL, in conjunction with object discovery methods, aid downstream tasks such as referring expression comprehension.