mlsanityData to 14 Oct 2026

Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection

arXiv 2510.00303 ↗First posted 30 Sep 2025cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Open-World Object Detection (OWOD) enriches traditional object detectors by enabling continual discovery and integration of unknown objects via human guidance. However, existing OWOD approaches frequently suffer from semantic confusion between known and unknown classes, alongside catastrophic forgetting, leading to diminished unknown recall and degraded known-class accuracy. To overcome these challenges, we propose Combinatorial Open-World Detection (CROWD), a unified framework reformulating unknown object discovery and adaptation as an interwoven combinatorial (set-based) data-discovery (CROWD-Discover) and representation learning (CROWD-Learn) task. CROWD-Discover strategically mines unknown instances by maximizing Submodular Conditional Gain (SCG) functions, selecting representative examples distinctly dissimilar from known objects. Subsequently, CROWD-Learn employs novel combinatorial objectives that jointly disentangle known and unknown representations while maintaining discriminative coherence among known classes, thus mitigating confusion and forgetting. Extensive evaluations on OWOD benchmarks illustrate that CROWD achieves improvements of 2.83% and 2.05% in known-class accuracy on M-OWODB and S-OWODB, respectively, and nearly 2.4x unknown recall compared to leading baselines.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 56 of its 76 references that are in the map. First posted on arXiv 30 Sep 2025.

Builds on

56 of 76 references.

References · 56

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2020End-to-End Object Detection with Transformerscited by 7,414
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  9. 2015Fast R-CNNcited by 2,933
  10. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  11. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  12. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
38 more
  1. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  2. 2019Gradient based sample selection for online continual learningcited by 571
  3. 2019Selection via Proxy: Efficient Data Selection for Deep Learningcited by 339
  4. 2021Towards Open World Object Detectioncited by 297
  5. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  6. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 158
  7. 2021Active Learning by Acquiring Contrastive Examplescited by 156
  8. 2021OW-DETR: Open-world Detection Transformercited by 129
  9. 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
  10. 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
  11. 2014Lazier Than Lazy Greedycited by 99
  12. 2020Submodular Combinatorial Information Measures with Applications in Machine Learningcited by 88
  13. 2020Optimal Continual Learning has Perfect Memory and is NP-hardcited by 87
  14. 2021Class-agnostic Object Detection with Multi-modal Transformercited by 85
  15. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 84
  16. 2019Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Visioncited by 64
  17. 2020Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNNcited by 61
  18. 2020Incremental Object Detection via Meta-Learningcited by 58
  19. 2022PROB: Probabilistic Objectness for Open World Object Detectioncited by 57
  20. 2021PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selectioncited by 51
  21. 2022UC-OWOD: Unknown-Classified Open World Object Detectioncited by 40
  22. 2022Submodularity In Machine Learning and Artificial Intelligencecited by 38
  23. 2021Effective Evaluation of Deep Active Learning on Image Classification Taskscited by 37
  24. 2023CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detectioncited by 28
  25. 2021TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Informationcited by 27
  26. 2023Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learningcited by 26
  27. 2023Random Boxes Are Open-world Object Detectorscited by 24
  28. 2022AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuningcited by 22
  29. 2022Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanismcited by 20
  30. 2021Objects in Semantic Topologycited by 18
  31. 2024Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learningcited by 18
  32. 2019Demystifying Multi-Faceted Video Summarization: Tradeoff Between Diversity,Representation, Coverage and Importancecited by 14
  33. 2021Few-Shot Learning for Road Object Detectioncited by 13
  34. 2024Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarkscited by 13
  35. 2024Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networkscited by 13
  36. 2022CLINICAL: Targeted Active Learning for Imbalanced Medical Image Classificationcited by 9
  37. 2018A Framework towards Domain Specific Video Summarizationcited by 8
  38. 2024Exploring Diverse Representations for Open Set Recognitioncited by 8

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Knowing the Unknown: Interpretable Open-World Object Detection via Concept Decomposition Modelcited by 1
  2. 2026SMA: Submodular Modality Aligner For Data Efficient Multimodal Learningcited by 1
  3. 2026Understanding Submodular Information Measure Based Objectives for Representation Learning: A Variance and Separation Perspectivecited by 0
  4. 2026Towards Sparsely Annotated Open-World Object Detectioncited by 0