Open-Set Recognition in the Age of Vision-Language Models

1 code implementation • 25 Mar 2024 • Dimity Miller, Niko Sünderhauf, Alex Kenna, Keita Mason

Are vision-language models (VLMs) for open-vocabulary perception inherently open-set models because they are trained on internet-scale datasets?

Open Set Learning

Uncertainty-Aware Lidar Place Recognition in Novel Environments

1 code implementation • 4 Oct 2022 • Keita Mason, Joshua Knights, Milad Ramezani, Peyman Moghadam, Dimity Miller

State-of-the-art lidar place recognition models exhibit unreliable performance when tested on environments different from their training dataset, which limits their use in complex and evolving environments.