DIDavid I. Inouye

David I. Inouye

*This is an algorithmically generated author record based on publicly available information.

David I. Inouye has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Enhanced Controllability of Diffusion Models via Feature Disentanglement and Realism-Enhanced Sampling Methods

    by Wonwoong Cho, Hareesh Ravi, Midhun Harikumar, Vinh Khuc, Krishna Kumar Singh, Jingwan Lu, David Inouye, Ajinkya Kale


  • Open Access

    StyleUV: Diverse and High-fidelity UV Map Generative Model

    by Myunggi Lee, Wonwoong Cho, Moonheum Kim, David Inouye, Nojun Kwak

    Reconstructing 3D human faces in the wild with the 3D Morphable Model (3DMM) has become popular in recent years. While most prior work focuses on estimating more robust and accurate geometry, relatively little attention has been paid to improving the quality of the texture model. Meanwhile, with the advent of Generative Adversarial Networks (GANs), there has been great progress in reconstructing realistic 2D images. Recent work demonstrates that GANs trained with abundant high-quality UV maps can produce high-fidelity textures superior to those produced by existing methods. However, acquiring such high-quality UV maps is difficult because they are expensive to acquire, requiring laborious processes to refine. In this work, we present a novel UV map generative model that learns to generate diverse and realistic synthetic UV maps without requiring high-quality UV maps for training. Our proposed framework can be trained solely with in-the-wild images (i.e., UV maps are not required) by leveraging a combination of GANs and a differentiable renderer. Both quantitative and qualitative evaluations demonstrate that our proposed texture model produces more diverse and higher fidelity textures compared to existing methods.

  • A review of multivariate distributions for count data derived from the Poisson distribution

    by David I. Inouye, Eunho Yang, Genevera I. Allen, Pradeep Ravikumar

    The Poisson distribution has been widely studied and used for modeling univariate count‐valued data. However, multivariate generalizations of the Poisson distribution that permit dependencies have been far less popular. Yet, real‐world, high‐dimensional, count‐valued data found in word counts, genomics, and crime statistics, for example, exhibit rich dependencies and motivate the need for multivariate distributions that can appropriately model this data. We review multivariate distributions derived from the univariate Poisson, categorizing these models into three main classes: (1) where the marginal distributions are Poisson, (2) where the joint distribution is a mixture of independent multivariate Poisson distributions, and (3) where the node‐conditional distributions are derived from the Poisson. We discuss the development of multiple instances of these classes and compare the models in terms of interpretability and theory. Then, we empirically compare multiple models from each class on three real‐world datasets that have varying data characteristics from different domains, namely traffic accident data, biological next generation sequencing data, and text data. These empirical experiments develop intuition about the comparative advantages and disadvantages of each class of multivariate distribution that was derived from the Poisson. Finally, we suggest new research directions as explored in the subsequent Discussion section.WIREs Comput Stat2017, 9:e1398. doi: 10.1002/wics.1398This article is categorized under: Statistical and Graphical Methods of Data Analysis > Multivariate Analysis


  • Towards undistorted and noise-free speech in an MRI scanner: Correlation subtraction followed by spectral noise gating

    by Joshua M. Inouye, Silvia S. Blemker, David I. Inouye

    Noise cancellation in an MRI environment is difficult due to the high noise levels that are in the spectral range of human speech. This paper describes a two-step method to cancel MRI noise that combines operations in both the time domain (correlation subtraction) and the frequency domain (spectral noise gating). The resulting filtered recording has a noise power suppression of over 100 dB, a significant improvement over previously described techniques on MRI noise cancellation. The distortion is lower and the noise suppression higher than using spectral noise gating in isolation. Implementation of this method will aid in detailed studies of speech in relation to vocal tract and velopharyngeal function.


  • Summarization of Twitter Microblogs

    by Beaux P. Sharifi, David I. Inouye, Jugal K. Kalita

    Owing to the sheer volume of text generated by a microblog site like Twitter, it is often difficult to fully understand what is being said about various topics. This paper presents algorithms for summarizing microblog documents. Initially, we present algorithms that produce single-document summaries but later extend them to produce summaries containing multiple documents. We evaluate the generated summaries by comparing them to both manually produced summaries and, for the multiple-post summaries, to the summarization results of some of the leading traditional summarization systems.


  • Comparing Twitter Summarization Algorithms for Multiple Post Summaries

    by David Inouye, Jugal K. Kalita

    Due to the sheer volume of text generated by a micro log site like Twitter, it is often difficult to fully understand what is being said about various topics. In an attempt to understand micro logs better, this paper compares algorithms for extractive summarization of micro log posts. We present two algorithms that produce summaries by selecting several posts from a given set. We evaluate the generated summaries by comparing them to both manually produced summaries and summaries produced by several leading traditional summarization systems. In order to shed light on the special nature of Twitter posts, we include extensive analysis of our results, some of which are unexpected.