mlsanityData to 7 Oct 2026

Addressing the Challenges of Open-World Object Detection

arXiv 2303.14930 ↗First posted 27 Mar 2023cs.CVcited by 2

Not on the map. Why?

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).

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 31 references that are in the map. First posted on arXiv 27 Mar 2023.

Builds on

23 of 31 references.

References · 23

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  6. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  7. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  8. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  9. 2021Towards Open World Object Detectioncited by 297
  10. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  11. 2021OW-DETR: Open-world Detection Transformercited by 129
  12. 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
11 more
  1. 2018Continuous Learning in Single-Incremental-Task Scenarioscited by 109
  2. 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
  3. 2022PROB: Probabilistic Objectness for Open World Object Detectioncited by 57
  4. 2018Evaluating Merging Strategies for Sampling-based Uncertainty Techniques in Object Detectioncited by 51
  5. 2022Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinitycited by 41
  6. 2022UC-OWOD: Unknown-Classified Open World Object Detectioncited by 40
  7. 2021Learning to Detect Every Thing in an Open Worldcited by 37
  8. 2020SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillationcited by 32
  9. 2023CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detectioncited by 28
  10. 2021Uncertainty for Identifying Open-Set Errors in Visual Object Detectioncited by 26
  11. 2020Towards Class-incremental Object Detection with Nearest Mean of Exemplarscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024Open World Object Detection: A Surveycited by 13
  2. 2026Towards Open World Sound Event Detectioncited by 0