ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation

被引:0
作者
Chen, Yangyi [1 ]
Wang, Xingyao [1 ]
Lie, Manling [2 ]
Hoiem, Derek [1 ]
Ji, Heng [1 ]
机构
[1] Univ Illinois, Urbana, IL 61801 USA
[2] Northwestern Univ, Evanston, IL USA
来源
2023 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2023) | 2023年
关键词
LANGUAGE;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
State-of-the-art vision-language models (VLMs) still have limited performance in structural knowledge extraction, such as relations between objects. In this work, we present ViStruct, a training framework to learn VLMs for effective visual structural knowledge extraction. Two novel designs are incorporated. First, we propose to leverage the inherent structure of programming language to depict visual structural information. This approach enables explicit and consistent representation of visual structural information of multiple granularities, such as concepts, relations, and events, in a well-organized structured format. Second, we introduce curriculum-based learning for VLMs to progressively comprehend visual structures, from fundamental visual concepts to intricate event structures. Our intuition is that lower-level knowledge may contribute to complex visual structure understanding. Furthermore, we compile and release a collection of datasets tailored for visual structural knowledge extraction. We adopt a weakly-supervised approach to directly generate visual event structures from captions for ViStruct training, capitalizing on abundant image-caption pairs from the web. In experiments, we evaluate ViStruct on visual structure prediction tasks, demonstrating its effectiveness in improving the understanding of visual structures. The code is public at https://github.com/Yangyi-Chen/vi-struct.
引用
收藏
页码:13342 / 13357
页数:16
相关论文
共 92 条
  • [1] VQA: Visual Question Answering
    Antol, Stanislaw
    Agrawal, Aishwarya
    Lu, Jiasen
    Mitchell, Margaret
    Batra, Dhruv
    Zitnick, C. Lawrence
    Parikh, Devi
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 2425 - 2433
  • [2] Baker C. F., 1998, P 17 INT C COMP LING, DOI DOI 10.3115/980845.980860
  • [3] Bengio Y., 2009, P INT C MACH LEARN, P41, DOI [DOI 10.1145/1553374.1553380, 10.1145/1553374.1553380]
  • [4] Biesialska Magdalena, 2020, P 28 INT C COMPUTATI, P6523
  • [5] Bird Steven, 2009, Nat-ural language processing with Python: analyzing text with the natural language toolkit
  • [6] Bravo Maria A, 2022, ARXIV
  • [7] Chen K., 2023, ARXIV
  • [8] Chen VS, 2019, IEEE I CONF COMP VIS, P2580, DOI [10.1109/ICCV.2019.00267, 10.1109/iccv.2019.00267]
  • [9] Chen YY, 2024, Arxiv, DOI arXiv:2309.04461
  • [10] Collaborative Transformers for Grounded Situation Recognition
    Cho, Junhyeong
    Yoon, Youngseok
    Kwak, Suha
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 19627 - 19636