Detecting Unknown Objects via Energy-based Separation for Open World Object Detection 事件

Detecting Unknown Objects via Energy-based Separation for Open World Object Detection arXiv:2603.29954v2 Announce Type: replace Abstract: 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 catastroph