{"ID":2857448,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.09173","arxiv_id":"2510.09173","title":"Beyond Flat Unknown Labels in Open-World Object Detection","abstract":"Most object detectors operate under a closed-world assumption, recognizing only the classes annotated in the training dataset and failing when encountering novel objects. Open-World Object Detection (OWOD) relaxes this assumption by enabling unseen objects to be detected as \"Unknown\". However, collapsing all novel objects into a single undifferentiated label eliminates semantic granularity and limits informed decision-making. In this paper, we introduce BOUND, an open-world detector that advances OWOD by inferring coarse-grained categories of unknown objects rather than merely flagging their existence. This enriched representation offers semantic cues that may benefit real-world systems. For example, in autonomous driving, distinguishing between an \"Unknown Animal\" (requiring yielding) and an \"Unknown Debris\" (requiring rerouting) leads to fundamentally different planning behaviors. Technically, BOUND integrates a sparsemax-based head for modeling objectness, a hierarchy-guided relabeling component that provides auxiliary supervision, and a classification module that learns hierarchical relationships. Experiments on OWOD benchmarks demonstrate that BOUND achieves higher unknown recall than existing baselines without sacrificing known-class mAP, while additionally enabling structured hierarchical categorization of unknown instances. Furthermore, evaluations on the long-tail LVIS dataset demonstrate robust generalization. Code will be made available.","short_abstract":"Most object detectors operate under a closed-world assumption, recognizing only the classes annotated in the training dataset and failing when encountering novel objects. Open-World Object Detection (OWOD) relaxes this assumption by enabling unseen objects to be detected as \"Unknown\". However, collapsing all novel obje...","url_abs":"https://arxiv.org/abs/2510.09173","url_pdf":"https://arxiv.org/pdf/2510.09173v2","authors":"[\"Yuchen Zhang\",\"Yao Lu\",\"Johannes Betz\"]","published":"2025-10-10T09:15:26Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}