English

Deep Multimodal Transfer-Learned Regression in Data-Poor Domains

Computer Vision and Pattern Recognition 2020-06-17 v1 Machine Learning

Abstract

In many real-world applications of deep learning, estimation of a target may rely on various types of input data modes, such as audio-video, image-text, etc. This task can be further complicated by a lack of sufficient data. Here we propose a Deep Multimodal Transfer-Learned Regressor (DMTL-R) for multimodal learning of image and feature data in a deep regression architecture effective at predicting target parameters in data-poor domains. Our model is capable of fine-tuning a given set of pre-trained CNN weights on a small amount of training image data, while simultaneously conditioning on feature information from a complimentary data mode during network training, yielding more accurate single-target or multi-target regression than can be achieved using the images or the features alone. We present results using phase-field simulation microstructure images with an accompanying set of physical features, using pre-trained weights from various well-known CNN architectures, which demonstrate the efficacy of the proposed multimodal approach.

Keywords

Cite

@article{arxiv.2006.09310,
  title  = {Deep Multimodal Transfer-Learned Regression in Data-Poor Domains},
  author = {Levi McClenny and Mulugeta Haile and Vahid Attari and Brian Sadler and Ulisses Braga-Neto and Raymundo Arroyave},
  journal= {arXiv preprint arXiv:2006.09310},
  year   = {2020}
}
R2 v1 2026-06-23T16:22:49.118Z