The Rochester Data Science Consortium is attending (virtually) the 2020 Computer Vision and Pattern Recognition (CVPR) Conference, taking place entirely online due to COVID-19 precautions. From June 14th – June 19th, over 6,500 attendees will gather, virtually, to take part in this premier annual computer vision event.
Scientists from the Rochester Data Science Consortium will be presenting original research at the 2020 CVPR conference, attending tutorials, workshops, and networking with other scientists in the Computer Vision and Pattern Recognition fields.
We consider the topic of data imputation, a foundational task in machine learning that addresses issues with missing data. To that end, we propose MCFlow, a deep framework for imputation that leverages normalizing flow generative models and Monte Carlo sampling. We address the causality dilemma that arises when training models with incomplete data by introducing an iterative learning scheme which alternately updates the density estimate and the values of the missing entries in the training data. We provide extensive empirical validation of the effectiveness of the proposed method on standard multivariate and image datasets, and benchmark its performance against state-of-the-art alternatives. We demonstrate that MCFlow is superior to competing methods in terms of the quality of the imputed data, as well as with regards to its ability to preserve the semantic structure of the data.
The 2020 Computer Vision and Pattern Recognition (CVPR) Conference is the premier annual computer vision event. With its high quality and low cost, it provides an exceptional value for students, academics and industry researchers.
You can find more information about this year’s 2020 CVPR Conference, taking place virtually, here.