Published in Artificial Intelligence. PDF.

"Open world" environments are those in which novel objects, agents, events, and more can appear and contradict previous understandings of the environment. This contradicts the "closed world" assumption used in most AI research, where the environment is assumed to be fully understood and unchanging. The …

Under review for ICML 2024. arXiv version.

The information noise-contrastive estimation (InfoNCE) loss function provides the basis of many self-supervised deep learning methods due to its strong empirical results and theoretic motivation. Previous work suggests a supervised contrastive (SupCon) loss to extend InfoNCE to learn from available class labels. However …

Published in TMLR. arXiv version.

In order for artificial agents to successfully perform tasks in changing environments, they must be able to both detect and adapt to novelty. However, visual novelty detection research often only evaluates on repurposed datasets such as CIFAR-10 originally intended for object classification, where images focus …

Published in ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning. arXiv version.

The pixelwise reconstruction error of deep autoencoders is often utilized for image novelty detection and localization under the assumption that pixels with high error indicate which parts of the input image are unfamiliar and therefore likely …

Published in 2019 IEEE Applied Imagery Pattern Recognition Workshop. arXiv version.

Designing robust activity detectors for fixed camera surveillance video requires knowledge of the 3-D scene. This paper presents an automatic camera calibration process that provides a mechanism to reason about the spatial proximity between objects at different times. It …