no code implementations • 23 May 2022 • John Kirchenbauer, Jacob Oaks, Eric Heim
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.
no code implementations • 7 Apr 2022 • Violet Turri, Rachel Dzombak, Eric Heim, Nathan VanHoudnos, Jay Palat, Anusha Sinha
Current test and evaluation (T&E) methods for assessing machine learning (ML) system performance often rely on incomplete metrics.
no code implementations • 2 Dec 2019 • Namjoon Suh, Xiaoming Huo, Eric Heim, Lee Seversky
We propose a combined model, which integrates the latent factor model and the logistic regression model, for the citation network.
4 code implementations • 21 Nov 2019 • Ritwik Gupta, Richard Hosfelt, Sandra Sajeev, Nirav Patel, Bryce Goodman, Jigar Doshi, Eric Heim, Howie Choset, Matthew Gaston
xBD is the largest building damage assessment dataset to date, containing 850, 736 building annotations across 45, 362 km\textsuperscript{2} of imagery.
Ranked #5 on 2D Semantic Segmentation on xBD
no code implementations • CVPR 2019 • Eric Heim
In our experiments, we show that our GAN framework is able to generate images that are of comparable quality to equivalent unsupervised GANs while satisfying a large number of the constraints provided by users, effectively changing a GAN into one that allows users interactive control over image generation without sacrificing image quality.
no code implementations • 15 Nov 2018 • Matthew Klawonn, Eric Heim, James Hendler
To that end, we develop an online algorithm that works in conjunction with classifier and training algorithm, iteratively selecting training data for the classifier based on how well it appears to generalize on each class.
no code implementations • 7 Feb 2018 • Matthew Klawonn, Eric Heim
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.
no code implementations • 25 Nov 2016 • Eric Heim, Alexander Seitel, Jonas Andrulis, Fabian Isensee, Christian Stock, Tobias Ross, Lena Maier-Hein
Using a total of 29, 000 crowd annotations performed on publicly available data of different object classes, we show that (1) our method is highly accurate in estimating the segmentation quality based on clickstream data, (2) outperforms state-of-the-art methods for merging multiple annotations.
no code implementations • 6 Nov 2015 • Eric Heim, Matthew Berger, Lee Seversky, Milos Hauskrecht
A common way to learn such a model is from relative comparisons in the form of triplets: responses to queries of the form "Is object a more similar to b than it is to c?".
no code implementations • 28 Jul 2015 • Eric Heim, Milos Hauskrecht
Finally, we perform qualitative assessments on the metrics learned by CAMEL and show that they identify and clearly articulate important factors in how the model performs inference.
no code implementations • 6 Jan 2015 • Eric Heim, Matthew Berger, Lee M. Seversky, Milos Hauskrecht
Learning a kernel matrix from relative comparison human feedback is an important problem with applications in collaborative filtering, object retrieval, and search.
no code implementations • 2 Sep 2013 • Eric Heim, Hamed Valizadegan, Milos Hauskrecht
In this work, we explore methods for aiding the process of learning a kernel with the help of auxiliary kernels built from more easily extractable information regarding the relationships among objects.