A Simple Baseline for Weakly-Supervised Scene Graph Generation
Lists
Only you see this
Abstract
We investigate the weakly-supervised scene graph generation, which is a challenging task since no correspondence of label and object is provided. The previous work regards such correspondence as a latent variable which is iteratively updated via nested optimization of the scene graph generation objective. However, we further reduce the complexity by decoupling it into an efficient first-order graph matching module optimized via contrastive learning to obtain such correspondence, which is used to train a standard scene graph generation model. The extensive experiments show that such a simple pipeline can significantly surpass the previous state-of-the-art by more than 30% on the Visual Genome dataset, both in terms of graph matching accuracy and scene graph quality. We believe this work serves as a strong baseline for future research.
BibTeX
@inproceedings{shi2021simple,
author = {Jing Shi and Yiwu Zhong and Ning Xu and Yin Li and Chenliang Xu},
title = {{A Simple Baseline for Weakly-Supervised Scene Graph Generation}},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2021},
doi = {10.1109/iccv48922.2021.01608},
}Loading related content...