AI RESEARCH
Detecting Unknown Objects via Energy-based Separation for Open World Object Detection
arXiv CS.CV
•
ArXi:2603.29954v1 Announce Type: new In this work, we tackle the problem of Open World Object Detection (OWOD). This challenging scenario requires the detector to incrementally learn to classify known objects without forgetting while identifying unknown objects without supervision. Previous OWOD methods have enhanced the unknown discovery process and employed memory replay to mitigate catastrophic forgetting.