Share this page:

VisualBERT: A Simple and Performant Baseline for Vision and Language

Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang, in Arxiv, 2019.

Code

Download the full text


Abstract

We propose VisualBERT, a simple and flexible framework for modeling a broad range of vision-and-language tasks. VisualBERT consists of a stack of Transformer layers that implicitly align elements of an input text and regions in an associated input image with self-attention. We further propose two visually-grounded language model objectives for pre-training VisualBERT on image caption data. Experiments on four vision-and-language tasks including VQA, VCR, NLVR2, and Flickr30K show that VisualBERT outperforms or rivals with state-of-the-art models while being significantly simpler. Further analysis demonstrates that VisualBERT can ground elements of language to image regions without any explicit supervision and is even sensitive to syntactic relationships, tracking, for example, associations between verbs and image regions corresponding to their arguments.



A short version is publised at ACL 2020.
VisualBERT is intergrated into Facebook MMF library
Please see more anlaysis about VisualBERT in a recent paper by A. Singh, V. Goswami, V., and D. Parikh (2019)
VisualBERT is used as a baseline in Hateful Memes by Facebook Research

Bib Entry

@inproceedings{li2019visualbert,
  author = {Li, Liunian Harold and Yatskar, Mark and Yin, Da and Hsieh, Cho-Jui and Chang, Kai-Wei},
  title = {VisualBERT: A Simple and Performant Baseline for Vision and Language},
  booktitle = {Arxiv},
  year = {2019}
}

Related Publications

  • Unified Pre-training for Program Understanding and Generation

    Wasi Ahmad, Saikat Chakraborty, Baishakhi Ray, and Kai-Wei Chang, in NAACL, 2021.
    Full Text Abstract BibTeX Details
    Code summarization and generation empower conversion between programming language (PL) and natural language (NL), while code translation avails the migration of legacy code from one PL to another. This paper introduces PLBART, a sequence-to-sequence model capable of performing a broad spectrum of program and language understanding and generation tasks. PLBART is pre-trained on an extensive collection of Java and Python functions and associated NL text via denoising autoencoding. Experiments on code summarization in the English language, code generation, and code translation in seven programming languages show that PLBART outperforms or rivals state-of-the-art models. Moreover, experiments on discriminative tasks, e.g., program repair, clone detection, and vulnerable code detection, demonstrate PLBART’s effectiveness in program understanding. Furthermore, analysis reveals that PLBART learns program syntax, style (e.g., identifier naming convention), logical flow (e.g., if block inside an else block is equivalent to else if block) that are crucial to program semantics and thus excels even with limited annotations.
    @inproceedings{ahamd2021unified,
      title = {Unified Pre-training for Program Understanding and Generation},
      author = {Ahmad, Wasi and Chakraborty, Saikat and Ray, Baishakhi and Chang, Kai-Wei},
      booktitle = {NAACL},
      year = {2021}
    }
    
    Details
  • Weakly-Supervised VisualBERT: Pre-training Vision-and-Language Representations Without Parallel Images and Captions

    Liunian Harold Li, Haoxuan You, Zhecan Wang, Alireza Zareian, Shih-Fu Chang, and Kai-Wei Chang, in NAACL, 2021.
    Full Text Abstract BibTeX Details
    Pre-trained contextual vision-and-language (V&L) models have brought impressive performance improvement on various benchmarks. However, the paired text-image data required for pre-training are hard to collect and scale up. We investigate if a strong V&L representation model can be learned without text-image pairs. We propose Weakly-supervised VisualBERT with the key idea of conducting "mask-and-predict" pre-training on language-only and image-only corpora. Additionally, we introduce the object tags detected by an object recognition model as anchor points to bridge two modalities. Evaluation on four V&L benchmarks shows that Weakly-supervised VisualBERT achieves similar performance with a model pre-trained with paired data. Besides, pre-training on more image-only data further improves a model that already has access to aligned data, suggesting the possibility of utilizing billions of raw images available to enhance V&L models.
    @inproceedings{li2021weakly-supervised,
      author = {Li, Liunian Harold and You, Haoxuan and Wang, Zhecan and Zareian, Alireza and Chang, Shih-Fu and Chang, Kai-Wei},
      title = {	Weakly-Supervised VisualBERT: Pre-training Vision-and-Language Representations Without Parallel Images and Captions},
      booktitle = {NAACL},
      year = {2021}
    }
    
    Details
  • What Does BERT with Vision Look At?

    Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang, in ACL (short), 2020.
    Full Text Slides Video Code Abstract BibTeX Details
    Pre-trained visually grounded language models such as ViLBERT, LXMERT, and UNITER have achieved significant performance improvement on vision-and-language tasks but what they learn during pre-training remains unclear. In this work, we demonstrate that certain attention heads of a visually grounded language model actively ground elements of language to image regions. Specifically, some heads can map entities to image regions, performing the task known as entity grounding. Some heads can even detect the syntactic relations between non-entity words and image regions, tracking, for example, associations between verbs and regions corresponding to their arguments. We denote this ability as \emphsyntactic grounding. We verify grounding both quantitatively and qualitatively, using Flickr30K Entities as a testbed.
    @inproceedings{li2020what,
      author = {Li, Liunian Harold and Yatskar, Mark and Yin, Da and Hsieh, Cho-Jui and Chang, Kai-Wei},
      title = {What Does BERT with Vision Look At?},
      booktitle = {ACL (short)},
      presentation_id = {https://virtual.acl2020.org/paper_main.469.html},
      year = {2020}
    }
    
    Details
  • VisualBERT: A Simple and Performant Baseline for Vision and Language

    Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang, in Arxiv, 2019.
    Full Text Code Abstract BibTeX Details
    We propose VisualBERT, a simple and flexible framework for modeling a broad range of vision-and-language tasks. VisualBERT consists of a stack of Transformer layers that implicitly align elements of an input text and regions in an associated input image with self-attention. We further propose two visually-grounded language model objectives for pre-training VisualBERT on image caption data. Experiments on four vision-and-language tasks including VQA, VCR, NLVR2, and Flickr30K show that VisualBERT outperforms or rivals with state-of-the-art models while being significantly simpler. Further analysis demonstrates that VisualBERT can ground elements of language to image regions without any explicit supervision and is even sensitive to syntactic relationships, tracking, for example, associations between verbs and image regions corresponding to their arguments.
    @inproceedings{li2019visualbert,
      author = {Li, Liunian Harold and Yatskar, Mark and Yin, Da and Hsieh, Cho-Jui and Chang, Kai-Wei},
      title = {VisualBERT: A Simple and Performant Baseline for Vision and Language},
      booktitle = {Arxiv},
      year = {2019}
    }
    
    Details