Year: 2022
Type: preprint
Abstract: Designing efficient and reliable VQA systems remains a challenging problem, more so in the case of disaster management and response systems. In this work, we revisit fundamental combination methods like concatenation, addition and element-wise multiplication with modern image and text feature abstraction models. We design a simple and efficient system which outperforms pre-existing methods on the FloodNet dataset and achieves state-of-the-art performance. This simplified system requires significantly less training and inference time than modern VQA architectures. We also study the performance of various backbones and report their consolidated results. Code is available at https://github.com/sahilkhose/floodnet_vqa.
Source: arXiv (Cornell University)
Authors: Kane, Aditya, Khose, Sahil
Institution: Manipal Academy of Higher Education
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4281686961