A Likelihood Ratio-Based Approach to Segmenting Unknown Objects
Sign Up to like & getrecommendations! Published in 2024 at "International Journal of Computer Vision"
DOI: 10.1007/s11263-025-02509-0
Abstract: Addressing the Out-of-Distribution (OoD) segmentation task is a prerequisite for perception systems operating in an open-world environment. Large foundational models are frequently used in downstream tasks, however, their potential for OoD remains mostly unexplored. We… read more here.
Keywords: large foundational; unknown objects; segmentation; representation ... See more keywords