Eric Heim
YOU?
Author Swipe
View article: What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability
What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability Open
Classifier calibration has received recent attention from the machine learning community due both to its practical utility in facilitating decision making, as well as the observation that modern neural network classifiers are poorly calibr…
View article: Wet and dry plastic deposition in the western United States
Wet and dry plastic deposition in the western United States Open
<p>Eleven billion tons of plastic are projected to accumulate in the environment by 2025. Because plastics are persistent, they fragment into pieces that are susceptible to wind entrainment. Using high resolution spatial and temporal…
View article: Proceedings of NeurIPS 2020 Workshop on Artificial Intelligence for Humanitarian Assistance and Disaster Response
Proceedings of NeurIPS 2020 Workshop on Artificial Intelligence for Humanitarian Assistance and Disaster Response Open
These are the "proceedings" of the 2nd AI + HADR workshop which was held virtually on December 12, 2020 as part of the Neural Information Processing Systems conference. These are non-archival and merely serve as a way to collate all the pa…
View article: Proceedings of NeurIPS 2019 Workshop on Artificial Intelligence for Humanitarian Assistance and Disaster Response
Proceedings of NeurIPS 2019 Workshop on Artificial Intelligence for Humanitarian Assistance and Disaster Response Open
These are the "proceedings" of the 1st AI + HADR workshop which was held in Vancouver, Canada on December 13, 2019 as part of the Neural Information Processing Systems conference. These are non-archival and serve solely as a collation of a…
View article: Proceedings of NeurIPS 2019 Workshop on Artificial Intelligence for\n Humanitarian Assistance and Disaster Response
Proceedings of NeurIPS 2019 Workshop on Artificial Intelligence for\n Humanitarian Assistance and Disaster Response Open
These are the "proceedings" of the 1st AI + HADR workshop which was held in\nVancouver, Canada on December 13, 2019 as part of the Neural Information\nProcessing Systems conference. These are non-archival and serve solely as a\ncollation o…
View article: Factor Analysis on Citation, Using a Combined Latent and Logistic Regression Model
Factor Analysis on Citation, Using a Combined Latent and Logistic Regression Model Open
We propose a combined model, which integrates the latent factor model and the logistic regression model, for the citation network. It is noticed that neither a latent factor model nor a logistic regression model alone is sufficient to capt…
View article: Understanding and improving model representation of aerosol optical properties for a Chinese haze event measured during KORUS-AQ
Understanding and improving model representation of aerosol optical properties for a Chinese haze event measured during KORUS-AQ Open
KORUS-AQ was an international cooperative air quality field study in South Korea that measured local and remote sources of air pollution affecting the Korean peninsula during May–June 2016. Some of the largest aerosol mass concentrations w…
View article: xBD: A Dataset for Assessing Building Damage from Satellite Imagery
xBD: A Dataset for Assessing Building Damage from Satellite Imagery Open
We present xBD, a new, large-scale dataset for the advancement of change detection and building damage assessment for humanitarian assistance and disaster recovery research. Natural disaster response requires an accurate understanding of d…
View article: Exploiting Class Learnability in Noisy Data
Exploiting Class Learnability in Noisy Data Open
In many domains, collecting sufficient labeled training data for supervised machine learning requires easily accessible but noisy sources, such as crowdsourcing services or tagged Web data. Noisy labels occur frequently in data sets harves…
View article: Constrained Generative Adversarial Networks for Interactive Image Generation
Constrained Generative Adversarial Networks for Interactive Image Generation Open
Generative Adversarial Networks (GANs) have received a great deal of attention due in part to recent success in generating original, high-quality samples from visual domains. However, most current methods only allow for users to guide this…
View article: Creating xBD: A Dataset for Assessing Building Damage from Satellite Imagery
Creating xBD: A Dataset for Assessing Building Damage from Satellite Imagery Open
We present a preliminary report for xBD, a new large-scale dataset for the advancement of change detection and building damage assessment for humanitarian assistance and disaster recovery research.Logistics, resource planning, and damage e…
View article: Exploiting Class Learnability in Noisy Data
Exploiting Class Learnability in Noisy Data Open
In many domains, collecting sufficient labeled training data for supervised machine learning requires easily accessible but noisy sources, such as crowdsourcing services or tagged Web data. Noisy labels occur frequently in data sets harves…
View article: Generating Triples With Adversarial Networks for Scene Graph Construction
Generating Triples With Adversarial Networks for Scene Graph Construction Open
Driven by successes in deep learning, computer vision research has begun to move beyond object detection and image classification to more sophisticated tasks like image captioning or visual question answering. Motivating such endeavors is …
View article: Large-scale medical image annotation with quality-controlled crowdsourcing
Large-scale medical image annotation with quality-controlled crowdsourcing Open
Accurate annotations of medical images are essential for various clinical applications. The remarkable advances in machine learning, especially deep learning based techniques, show great potential for automatic image segmentation. However,…
View article: Clickstream Analysis for Crowd-Based Object Segmentation with Confidence
Clickstream Analysis for Crowd-Based Object Segmentation with Confidence Open
With the rapidly increasing interest in machine learning based solutions for automatic image annotation, the availability of reference annotations for algorithm training is one of the major bottlenecks in the field. Crowdsourcing has evolv…