# Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection

arXiv: https://arxiv.org/abs/2306.14291 · HTML: https://mlsanity.com/paper/2306.14291/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 25 Jun 2023.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry](https://mlsanity.com/paper/1806.03417/) (2018)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [Hyperbolic Image Embeddings](https://mlsanity.com/paper/1904.02239/) (2019)
- [OW-DETR: Open-world Detection Transformer](https://mlsanity.com/paper/2112.01513/) (2021)
- [Hyperbolic Vision Transformers: Combining Improvements in Metric Learning](https://mlsanity.com/paper/2203.10833/) (2022)
- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix](https://mlsanity.com/paper/2010.04003/) (2020)
- [Class-agnostic Object Detection with Multi-modal Transformer](https://mlsanity.com/paper/2111.11430/) (2021)
- [Hyperbolic Contrastive Learning for Visual Representations beyond Objects](https://mlsanity.com/paper/2212.00653/) (2022)
- [PROB: Probabilistic Objectness for Open World Object Detection](https://mlsanity.com/paper/2212.01424/) (2022)
- [Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity](https://mlsanity.com/paper/2204.06107/) (2022)
- [UC-OWOD: Unknown-Classified Open World Object Detection](https://mlsanity.com/paper/2207.11455/) (2022)
- [Learning to Detect Every Thing in an Open World](https://mlsanity.com/paper/2112.01698/) (2021)
- [Continual Object Detection: A review of definitions, strategies, and challenges](https://mlsanity.com/paper/2205.15445/) (2022)
- [Class-agnostic Object Detection](https://mlsanity.com/paper/2011.14204/) (2020)
- [Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders](https://mlsanity.com/paper/2103.16046/) (2021)
- [Hyperbolic Contrastive Learning](https://mlsanity.com/paper/2302.01409/) (2023)
- [Object Detection in Autonomous Vehicles: Status and Open Challenges](https://mlsanity.com/paper/2201.07706/) (2022)
- [On Hyperbolic Embeddings in 2D Object Detection](https://mlsanity.com/paper/2203.08049/) (2022)

## Built on by (most cited first, 15 of 15)

- [GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients](https://mlsanity.com/paper/2308.00310/) (2023)
- [Open World Object Detection in the Era of Foundation Models](https://mlsanity.com/paper/2312.05745/) (2023)
- [From Open Vocabulary to Open World: Teaching Vision Language Models to Detect Novel Objects](https://mlsanity.com/paper/2411.18207/) (2024)
- [A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets](https://mlsanity.com/paper/2403.06295/) (2024)
- [BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models](https://mlsanity.com/paper/2510.20095/) (2025)
- [REAL-OW: Rehearsal-free Open World Object Detection with Low-Rank Adaptation and Dual-Stage Objectness Modeling](https://mlsanity.com/paper/2607.03004/) (2026)
- [OW-Rep: Open World Object Detection with Instance Representation Learning](https://mlsanity.com/paper/2409.16073/) (2024)
- [Balanced Hierarchical Contrastive Learning with Decoupled Queries for Fine-grained Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2512.24074/) (2025)
- [Beyond Known Objects: A Novel Framework for Open-Set Object Detection using Negative-Aware Norm](https://mlsanity.com/paper/2605.02284/) (2026)
- [Hyp2Former: Hierarchy-Aware Hyperbolic Embeddings for Open-Set Panoptic Segmentation](https://mlsanity.com/paper/2605.02580/) (2026)
- [DualMem: Bypassing the Objectness Bottleneck for Calibrated Unknown-Stream Filtering in Open-World Object Detection](https://mlsanity.com/paper/2605.23634/) (2026)
- [HyperANFIS: Enhancing Rule Representation and Interpretability in Adaptive Neuro-Fuzzy Systems via Hyperbolic Geometry](https://mlsanity.com/paper/2608.11768/) (2026)
- [Towards Sparsely Annotated Open-World Object Detection](https://mlsanity.com/paper/2608.12714/) (2026)
- [Hyperbolic Geometry for Open-World Object Detection in Remote Sensing Imagery](https://mlsanity.com/paper/2609.09626/) (2026)
- [Revisiting Triplet Contrastive Learning for 3D Shape Understanding](https://mlsanity.com/paper/2610.19519/) (2026)

## Abstract (arXiv)

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