ZeShot-VQA: Zero-Shot Visual Question Answering Framework with Answer Mapping for Natural Disaster Damage Assessment

TL;DR

ZeShot-VQA is a zero-shot visual question answering framework designed for natural disaster damage assessment, capable of answering open-ended questions without fine-tuning, thus enabling rapid deployment on new datasets.

Contribution

The paper introduces ZeShot-VQA, a novel zero-shot VQA method leveraging large-scale vision-language models for disaster assessment, eliminating the need for dataset-specific fine-tuning.

Findings

Effective on FloodNet dataset for post-disaster analysis

Can generate answers unseen during training

Operates without fine-tuning on new datasets

Abstract

Natural disasters usually affect vast areas and devastate infrastructures. Performing a timely and efficient response is crucial to minimize the impact on affected communities, and data-driven approaches are the best choice. Visual question answering (VQA) models help management teams to achieve in-depth understanding of damages. However, recently published models do not possess the ability to answer open-ended questions and only select the best answer among a predefined list of answers. If we want to ask questions with new additional possible answers that do not exist in the predefined list, the model needs to be fin-tuned/retrained on a new collected and annotated dataset, which is a time-consuming procedure. In recent years, large-scale Vision-Language Models (VLMs) have earned significant attention. These models are trained on extensive datasets and demonstrate strong performance on both unimodal and multimodal vision/language downstream tasks, often without the need for fine-tuning. In this paper, we propose a VLM-based zero-shot VQA (ZeShot-VQA) method, and investigate the performance of on post-disaster FloodNet dataset. Since the proposed method takes advantage of zero-shot learning, it can be applied on new datasets without fine-tuning. In addition, ZeShot-VQA is able to process and generate answers that has been not seen during the training procedure, which demonstrates its flexibility.