Zobrazeno 1 - 10
of 74
pro vyhledávání: '"Heim, Eric"'
Artificial intelligence (AI) has revolutionized decision-making processes and systems throughout society and, in particular, has emerged as a significant technology in high-impact scenarios of national interest. Yet, despite AI's impressive predictiv
Externí odkaz:
http://arxiv.org/abs/2408.01301
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 calibrated. Much
Externí odkaz:
http://arxiv.org/abs/2205.11454
Current test and evaluation (T&E) methods for assessing machine learning (ML) system performance often rely on incomplete metrics. Testing is additionally often siloed from the other phases of the ML system lifecycle. Research investigating cross-dom
Externí odkaz:
http://arxiv.org/abs/2204.04211
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 papers accept
Externí odkaz:
http://arxiv.org/abs/2012.02108
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 capture the str
Externí odkaz:
http://arxiv.org/abs/1912.00524
Autor:
Gupta, Ritwik, Hosfelt, Richard, Sajeev, Sandra, Patel, Nirav, Goodman, Bryce, Doshi, Jigar, Heim, Eric, Choset, Howie, Gaston, Matthew
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 damaged buil
Externí odkaz:
http://arxiv.org/abs/1911.09296
Autor:
Heim, Eric
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 image gene
Externí odkaz:
http://arxiv.org/abs/1904.02526
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 harvested via the
Externí odkaz:
http://arxiv.org/abs/1811.06524
Autor:
Klawonn, Matthew, Heim, Eric
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 the desire
Externí odkaz:
http://arxiv.org/abs/1802.02598
Autor:
Heim, Eric, Seitel, Alexander, Andrulis, Jonas, Isensee, Fabian, Stock, Christian, Ross, Tobias, Maier-Hein, Lena
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 evolved as a val
Externí odkaz:
http://arxiv.org/abs/1611.08527