# Addressing the Challenges of Open-World Object Detection

arXiv: https://arxiv.org/abs/2303.14930 · HTML: https://mlsanity.com/paper/2303.14930/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 27 Mar 2023.

## Builds on (most cited first, 23 of 23)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [Incremental Learning of Object Detectors without Catastrophic Forgetting](https://mlsanity.com/paper/1708.06977/) (2017)
- [OW-DETR: Open-world Detection Transformer](https://mlsanity.com/paper/2112.01513/) (2021)
- [Dropout Sampling for Robust Object Detection in Open-Set Conditions](https://mlsanity.com/paper/1710.06677/) (2017)
- [Continuous Learning in Single-Incremental-Task Scenarios](https://mlsanity.com/paper/1806.08568/) (2018)
- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [PROB: Probabilistic Objectness for Open World Object Detection](https://mlsanity.com/paper/2212.01424/) (2022)
- [Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detection](https://mlsanity.com/paper/1809.06006/) (2018)
- [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)
- [SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillation](https://mlsanity.com/paper/2012.15439/) (2020)
- [CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection](https://mlsanity.com/paper/2301.01970/) (2023)
- [Uncertainty for Identifying Open-Set Errors in Visual Object Detection](https://mlsanity.com/paper/2104.01328/) (2021)
- [Towards Class-incremental Object Detection with Nearest Mean of Exemplars](https://mlsanity.com/paper/2008.08336/) (2020)

## Built on by (most cited first, 2 of 2)

- [Open World Object Detection: A Survey](https://mlsanity.com/paper/2410.11301/) (2024)
- [Towards Open World Sound Event Detection](https://mlsanity.com/paper/2605.03934/) (2026)

## Abstract (arXiv)

We address the challenging problem of open world object detection (OWOD), where object detectors must identify objects from known classes while also identifying and continually learning to detect novel objects. Prior work has resulted in detectors that have a relatively low ability to detect novel objects, and a high likelihood of classifying a novel object as one of the known classes. We approach the problem by identifying the three main challenges that OWOD presents and introduce OW-RCNN, an open world object detector that addresses each of these three challenges. OW-RCNN establishes a new state of the art using the open-world evaluation protocol on MS-COCO, showing a drastically increased ability to detect novel objects (16-21% absolute increase in U-Recall), to avoid their misclassification as one of the known classes (up to 52% reduction in A-OSE), and to incrementally learn to detect them while maintaining performance on previously known classes (1-6% absolute increase in mAP).