TinyVQA: Compact Multimodal Deep Neural Network for Visual Question Answering on Resource-Constrained Devices

arXiv:2404.03574v1 Announce Type: cross
Abstract: Traditional machine learning models often require powerful hardware, making them unsuitable for deployment on resource-limited devices. Tiny Machine Learning (tinyML) has emerged as a promising approach for running machine learning models on these devices, but integrating multiple data modalities into tinyML models still remains a challenge due to increased complexity, latency, and power consumption. This paper proposes TinyVQA, a novel multimodal deep neural network for visual question answering tasks that can be deployed on resource-constrained …

abstract arxiv compact cs.ai cs.cv cs.lg data deep neural network deployment devices hardware machine machine learning machine learning models making multimodal multiple network neural network question question answering running them tinyml traditional machine learning type visual