no code implementations • 23 Dec 2023 • YanMing Zhang, Brette Fitzgibbon, Dino Garofolo, Akshith Kota, Eric Papenhausen, Klaus Mueller
We propose the use of large language models such as ChatGPT as an auditor for causal networks.
no code implementations • 23 Dec 2023 • Eli Dugan, Klaus Mueller
This paper deals with developing techniques for the reconstruction of high-dimensional datasets given each bivariate projection, as would be found in a matrix scatterplot.
no code implementations • 12 Mar 2023 • Jun Wang, Klaus Mueller
Furthermore, since an effect can be a cause of other effects, we allow users to aggregate different temporal cause-effect relations found with our method into a visual flow diagram to enable the discovery of temporal causal networks.
no code implementations • 7 Feb 2023 • Soham Bhosale, Arjun Krishna, Ge Wang, Klaus Mueller
The augmented dataset is then used to train a U-Net segmentation network which displays a significant improvement in the segmentation accuracy in segmenting the large non-annotated dataset.
no code implementations • 27 Dec 2022 • Ashley Liew, Klaus Mueller
Creating compelling captions for data visualizations has been a longstanding challenge.
no code implementations • 10 Aug 2022 • Bhavya Ghai, Klaus Mueller
A user can detect the presence of bias against a group, say females, or a subgroup, say black females, by identifying unfair causal relationships in the causal network and using an array of fairness metrics.
no code implementations • 29 Jul 2022 • Ayush Kumar, Ashish Kumar, Aakanksha Prasad, Michael Burch, Shenghui Cheng, Klaus Mueller
We illustrate the usefulness of our tool by applying it to the eye movements of 216 programmers of multiple expertise levels that were collected during two code comprehension tasks.
1 code implementation • 21 Apr 2022 • Anjul Tyagi, Jian Zhao, Pushkar Patel, Swasti Khurana, Klaus Mueller
With the help of designers, we propose a semi-automated infographic framework for general structured and flow-based infographic design generation.
1 code implementation • 8 Feb 2022 • Bhavya Ghai, Mihir Mishra, Klaus Mueller
Lastly, we offer a list of combinations of interventions that perform best for different fairness and utility metrics to aid the design of fair ML pipelines.
no code implementations • 26 Aug 2021 • Anjul Tyagi, Jian Zhao, Pushkar Patel, Swasti Khurana, Klaus Mueller
Based on the framework, we also propose an interactive tool, \name{}, for assisting novice designers with creating high-quality infographics from an input in a markdown format by offering recommendations of different design components of infographics.
1 code implementation • 23 Aug 2021 • Bhavya Ghai, Klaus Mueller
On hovering over any such word, Fluent presents a set of alternative words which have similar meaning but are easier to speak.
1 code implementation • 29 May 2021 • Heyi Li, Jinlong Liu, Xinyu Zhang, Yunzhi Bai, Huayan Wang, Klaus Mueller
But more importantly, the proposed $W$++ space achieves superior performance in both reconstruction quality and editing quality.
no code implementations • 18 Mar 2021 • Arjun Krishna, Kedar Bartake, Chuang Niu, Ge Wang, Youfang Lai, Xun Jia, Klaus Mueller
Deep learning has shown great promise for CT image reconstruction, in particular to enable low dose imaging and integrated diagnostics.
1 code implementation • 5 Mar 2021 • Bhavya Ghai, Md Naimul Hoque, Klaus Mueller
In this work, we present WordBias, an interactive visual tool designed to explore biases against intersectional groups encoded in static word embeddings.
no code implementations • 18 Feb 2021 • Chuang Niu, Ge Wang, Pingkun Yan, Juergen Hahn, Youfang Lai, Xun Jia, Arjun Krishna, Klaus Mueller, Andreu Badal, KyleJ. Myers, Rongping Zeng
We propose a Noise Entangled GAN (NE-GAN) for simulating low-dose computed tomography (CT) images from a higher dose CT image.
no code implementations • 28 Sep 2020 • Anjul Tyagi, Cong Xie, Klaus Mueller
To deal with the problem, we formulate the task of neural network architecture optimization as a graph space exploration, based on the one-shot architecture search technique.
no code implementations • 6 Sep 2020 • Bhavya Ghai, Q. Vera Liao, Yunfeng Zhang, Klaus Mueller
The similarity score between feature rankings provided by the annotator and the local model explanation is used to assign a weight to each corresponding committee model.
no code implementations • 4 Apr 2020 • Bhavya Ghai, Q. Vera Liao, Yunfeng Zhang, Klaus Mueller
Social biases based on gender, race, etc.
no code implementations • 24 Jan 2020 • Bhavya Ghai, Q. Vera Liao, Yunfeng Zhang, Rachel Bellamy, Klaus Mueller
We conducted an empirical study comparing the model learning outcomes, feedback content and experience with XAL, to that of traditional AL and coactive learning (providing the model's prediction without the explanation).
no code implementations • 17 Jan 2020 • Heyi Li, Yuewei Lin, Klaus Mueller, Wei Xu
Using the Galaxy Zoo dataset we demonstrate that our method clearly reveals attention areas of the Discriminator when differentiating generated galaxy images from ground truth images.
no code implementations • 29 Oct 2019 • Bhavya Ghai, Buvana Ramanan, Klaus Mueller
Thereafter, we tried to investigate if we can use publicly available noisy data to train robust ASR systems.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 29 Jul 2019 • Ayush Kumar, Anjul Tyagi, Michael Burch, Daniel Weiskopf, Klaus Mueller
Yarbus' claim to decode the observer's task from eye movements has received mixed reactions.
no code implementations • 6 Aug 2018 • Sungsoo Ha, Klaus Mueller
We tested the proposed method with two clinical datasets that were both obtained during spine surgery.
2 code implementations • 22 Dec 2017 • Heyi Li, Yunke Tian, Klaus Mueller, Xin Chen
In this paper, we propose a novel two-step understanding method, namely Salient Relevance (SR) map, which aims to shed light on how deep CNNs recognize images and learn features from areas, referred to as attention areas, therein.
no code implementations • 20 Nov 2016 • Salman Mahmood, Rami Al-Rfou, Klaus Mueller
Neural network based models are a very powerful tool for creating word embeddings, the objective of these models is to group similar words together.