# Beyond Flat Unknown Labels in Open-World Object Detection

arXiv: https://arxiv.org/abs/2510.09173 · HTML: https://mlsanity.com/paper/2510.09173/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification](https://mlsanity.com/paper/1602.02068/) (2016)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [Adaptively Sparse Transformers](https://mlsanity.com/paper/1909.00015/) (2019)
- [OW-DETR: Open-world Detection Transformer](https://mlsanity.com/paper/2112.01513/) (2021)
- [Exploiting Unlabeled Data with Vision and Language Models for Object Detection](https://mlsanity.com/paper/2207.08954/) (2022)
- [Open Vocabulary Object Detection with Pseudo Bounding-Box Labels](https://mlsanity.com/paper/2111.09452/) (2021)
- [Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2303.05892/) (2023)
- [Selective Attention for Context-aware Neural Machine Translation](https://mlsanity.com/paper/1903.08788/) (2019)
- [PROB: Probabilistic Objectness for Open World Object Detection](https://mlsanity.com/paper/2212.01424/) (2022)
- [UC-OWOD: Unknown-Classified Open World Object Detection](https://mlsanity.com/paper/2207.11455/) (2022)
- [Hierarchical Novelty Detection for Visual Object Recognition](https://mlsanity.com/paper/1804.00722/) (2018)
- [Random Boxes Are Open-world Object Detectors](https://mlsanity.com/paper/2307.08249/) (2023)
- [Conditional Probability Tree Estimation Analysis and Algorithms](https://mlsanity.com/paper/1408.2031/) (2014)
- [A Hierarchical Semantic Distillation Framework for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2503.10152/) (2025)
- [Sparse and Structured Visual Attention](https://mlsanity.com/paper/2002.05556/) (2020)
- [The VISIONE Video Search System: Exploiting Off-the-Shelf Text Search Engines for Large-Scale Video Retrieval](https://mlsanity.com/paper/2008.02749/) (2020)

## Abstract (arXiv)

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.