April 18, 2024, 4:43 a.m. | Matthew Inkawhich, Nathan Inkawhich, Hao Yang, Jingyang Zhang, Randolph Linderman, Yiran Chen

cs.CV updates on arXiv.org arxiv.org

arXiv:2404.10865v1 Announce Type: new
Abstract: An object detector's ability to detect and flag \textit{novel} objects during open-world deployments is critical for many real-world applications. Unfortunately, much of the work in open object detection today is disjointed and fails to adequately address applications that prioritize unknown object recall \textit{in addition to} known-class accuracy. To close this gap, we present a new task called Open-Set Object Detection and Discovery (OSODD) and as a solution propose the Open-Set Regions with ViT features (OSR-ViT) …

abstract applications arxiv cs.cv deployments detection discovery framework modular novel object objects open-world recall set simple type vit work world

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Data Analyst (Digital Business Analyst)

@ Activate Interactive Pte Ltd | Singapore, Central Singapore, Singapore