# Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection Source: [Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection]() Collection index: [llms.txt]() Data updated: 2025-10-26T02:21:13.235Z Authors: Thang Doan, Xin Li, Sima Behpour, Wenbin He, Liang Gou, Liu Ren Published: 2023-06-25T16:45:20.000Z ## Abstract Open World Object Detection (OWOD) is a challenging and realistic task that extends beyond the scope of standard Object Detection task. It involves detecting both known and unknown objects while integrating learned knowledge for future tasks. However, the level of "unknownness" varies significantly depending on the context. For example, a tree is typically considered part of the background in a self-driving scene, but it may be significant in a household context. We argue that this contextual information should already be embedded within the known classes. In other words, there should be a semantic or latent structure relationship between the known and unknown items to be discovered. Motivated by this observation, we propose Hyp-OW, a method that learns and models hierarchical representation of known items through a SuperClass Regularizer. Leveraging this representation allows us to effectively detect unknown objects using a similarity distance-based relabeling module. Extensive experiments on benchmark datasets demonstrate the effectiveness of Hyp-OW, achieving improvement in both known and unknown detection (up to 6 percent). These findings are particularly pronounced in our newly designed benchmark, where a strong hierarchical structure exists between known and unknown objects. Our code can be found at https://github.com/boschresearch/Hyp-OW ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Open World Object Detection on S-OWODB](): Open World Object Detection; S-OWODB; mAP (Current Known): 72.7. - [Open World Object Detection on M-OWODB](): Open World Object Detection; M-OWODB; mAP (Current known): 59.4. - [Open-World Object Detection on M-OWODB Task 1](): Open World Object Detection; M-OWODB Task 1; U-Recall: 17.9. ## Original sources and implementation [Original paper]() [PDF]()