I am Jay Rothenberger, an Advanced AI Engineer at Honeywell Aerospace. I earned my Ph.D. in Computer Science from the University of Oklahoma (OU) in May 2026, advised by Dimitris Diochnos, and my B.S. in Computer Science and Mathematics from the University of Virginia. My research spans computer vision, representation learning, explainable AI, and deep learning, with a focus on semi-supervised learning and more data- and compute-efficient methods. I believe that the future is closer to the edge than it is to HPC. Before joining Honeywell full time I was an AI/ML research intern there, and I spent earlier summers doing machine learning research at LumenUs Scientific Solutions and Vaisala Xweather, including explainable AI for weather data. I am open to opportunities for research collaboration, so do not hesitate to contact me.
GitHub: https://github.com/JayRothenberger/Meta-Co-Training
ArXiv paper: https://arxiv.org/abs/2311.18083
In many practical computer vision scenarios unlabeled data is plentiful, but labels are scarce and difficult to obtain. As a result, semi-supervised learning which leverages unlabeled data to boost the performance of supervised classifiers have received significant attention in recent literature. One major class of semi-supervised algorithms is co-training. In co-training two different models leverage different independent and sufficient "views" of the data to jointly make better predictions. During co-training each model creates pseudo labels on unlabeled points which are used to improve the other model. We show that in the common case when independent views are not available we can construct such views inexpensively using pre-trained models. Co-training on the constructed views yields a performance improvement over any of the individual views we construct and performance comparable with recent approaches in semi-supervised learning, but has some undesirable properties. To alleviate the issues present with co-training we present Meta Co-Training which is an extension of the successful Meta Pseudo Labels approach to two views. Our method achieves new state-of-the-art performance on ImageNet-10% with very few training resources, as well as outperforming prior semi-supervised work on several other fine-grained image classification datasets.
email: jay.c.rothenberger@ou.edu
GitHub: https://github.com/JayRothenberger
Linkedin: https://www.linkedin.com/in/jay-rothenberger/