English

PiggyBack: Pretrained Visual Question Answering Environment for Backing up Non-deep Learning Professionals

Computer Vision and Pattern Recognition 2022-12-02 v3 Artificial Intelligence

Abstract

We propose a PiggyBack, a Visual Question Answering platform that allows users to apply the state-of-the-art visual-language pretrained models easily. The PiggyBack supports the full stack of visual question answering tasks, specifically data processing, model fine-tuning, and result visualisation. We integrate visual-language models, pretrained by HuggingFace, an open-source API platform of deep learning technologies; however, it cannot be runnable without programming skills or deep learning understanding. Hence, our PiggyBack supports an easy-to-use browser-based user interface with several deep learning visual language pretrained models for general users and domain experts. The PiggyBack includes the following benefits: Free availability under the MIT License, Portability due to web-based and thus runs on almost any platform, A comprehensive data creation and processing technique, and ease of use on deep learning-based visual language pretrained models. The demo video is available on YouTube and can be found at https://youtu.be/iz44RZ1lF4s.

Keywords

Cite

@article{arxiv.2211.15940,
  title  = {PiggyBack: Pretrained Visual Question Answering Environment for Backing up Non-deep Learning Professionals},
  author = {Zhihao Zhang and Siwen Luo and Junyi Chen and Sijia Lai and Siqu Long and Hyunsuk Chung and Soyeon Caren Han},
  journal= {arXiv preprint arXiv:2211.15940},
  year   = {2022}
}

Comments

Accepted by WSDM 2023

R2 v1 2026-06-28T07:16:16.606Z