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

TL;DR

PiggyBack is a user-friendly, web-based platform that enables non-experts to easily utilize state-of-the-art visual question answering models without deep learning expertise.

Contribution

It introduces a browser-based interface supporting full VQA tasks with pretrained models, making advanced visual-language AI accessible to general users and domain experts.

Findings

Supports multiple pretrained models via HuggingFace

Provides an easy-to-use visual interface

Enables quick deployment on various platforms

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.