Open-World Object Detection and Segmentation: Current Challenges and Emerging Opportunities

Muhammad Iqubal Ali (무하마드 이크발 알리); In-Chul Han (한인철); Soo Kyun Kim (김수균)

doi:10.20465/KIOTS.2025.11.6.233

Open-World Object Detection and Segmentation: Current Challenges and Emerging Opportunities

Journal of Internet of Things and Convergence
Abbr : JKIOTS
2025, 11(6), pp.241~248
DOI : 10.20465/KIOTS.2025.11.6.233
Publisher : The Korea Internet of Things Society
Research Area : Engineering > Computer Science > Internet Information Processing
Received : October 12, 2025
Accepted : December 15, 2025
Published : December 31, 2025

Muhammad Iqubal Ali ¹, In-Chul Han ², Soo Kyun Kim ²

¹제주대학교 컴퓨터공학과
²제주대학교

Accredited

ABSTRACT

Real-world vision systems often encounter categories unseen during training, challenging the closed-set limitation of traditional detectors. This review summarizes advances in Open-World Object Detection (OWOD) and its extension to open-world segmentation, where models must recognize known classes, reject novel instances, and incrementally learn new categories. We categorize OWOD approaches into pseudo-labeling, class-agnostic proposal learning, metric-based novelty scoring, and hybrid methods leveraging vision–language or video cues, connecting them to open-world semantic and instance segmentation. Key challenges include proposal bias, open-set misclassification, continual learning degradation, and inconsistent evaluation. Finally, we highlight future directions such as integration with 3D perception, self/semi-supervised learning, and calibrated uncertainty, outlining a roadmap toward reliable open-world perception.

KEYWORDS

Open-world Object Detection (OWOD), Open-World Segmentation, Open-Set Recognition, Unknown Detection, Incremental/Continual Learning

Journal Copyright Policy

No CCL information provided

Citation status

* References for papers published after 2025 are currently being built.

[confproc] Joseph.K.J / 2021 / Towards open world object detection / Proceeddings of the IEEE/CVF conference on computer vision and pattern recognition : 5830~5840

[confproc] Gupta.A / 2022 / Ow-detr: Open-world detection transformer / Proceddings of the IEEE/CVF conference on computer vision and pattern recognition : 9235~9244

[confproc] Zohar.O / 2023 / Prob:Probabilistic objectness for open world object detection / Proceddgins of the IEEE/CVF Conference on Computer Vision and Pattern Recognition : 11444~11453

[confproc] Ma.S / 2023 / Cat: Localization and identification cascade detection transformer for open-world object detection / Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition : 19681~19690

[journal] Zhao.X / 2023 / Revisiting open world object detection / IEEE Transactions of Circuits and Systems for Video Technology 34(5) : 3496~3509

[confproc] Wu.Z / 2022 / UC-OWOD: Unknown-classified open world object detection / European conference on computer vision / Springer Nature Switzerland : 193~210

[journal] Scheirer.W.J / 2012 / Toward open set recognition / transactions on pattern analysis and machine intelligence 35(7) : 1757~1772

[confproc] Bendale.A / 2016 / Toward open set deep networks / Proceedings of the IEEE conference on computer vision and pattern recognition : 1563~1572

[confproc] SodaNo.M / 2024 / Open-world semantic segmentation including class similarity / Proceedings of the IEEE/CVF conference on computer vision and pattern recognition : 3184~3194

[confproc] Kalluri.T / 2024 / Open-world instance segmentation: Top-down learning with bottom-up supervision / Proceddings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition : 2693~2703

[journal] Iqbal.M.A / 2023 / Improved open world object detection using class-wise feature space learning / IEEE Access 11 : 131221~131236

[journal] Iqbal.M.A / 2024 / Redefining Object Detection for Open-World Settings: A Framework for Simultaneous Identification of Known and Unknown Classes / IEEE Access

[other] Pershouse.D / 2023 / Addressing the challenges of open-world object detection / arXiv preprint

[confproc] Wang.Y / 2023 / Random boxes are open-world object detectors / Proceedings of the IEEE/CVF international coference on computer vision : 6233~6243

[confproc] Du.X / 2022 / Unknown-aware objec tdetection: Learning what you don't know from videos in the wild / Proceedings of the IEEE/CVF conference on computer vision and pattern recognition : 13678~13688

[confproc] Liang.W / 2023 / Unknown sniffer for object detection: Don't turn a blind eye to unknown objects / Proceedings of the IEEE/CVF conference on computer vision and pattern recognition : 3230~3239

[confproc] Yoshihashi.R / 2019 / Classification-reconstruction learning for open-set recognition / Proceedings of the IEEE/CVF conference on computer vision and pattern recognition : 4016~4025

[journal] Peng.C / 2020 / Faster ilod: Incremental learning for object detectors based on faster rcnn / Pattern recognition letters 140 : 109~115

[confproc] Zareian.A / 2021 / Open-vocabulary object detection using captions / Proceedings of the IEEE/CVF conference on computer vision and pattern recognition : 14393~14402

[journal] Iqbal, Muhammad Ali / 2025 / Tail-Calibrated Transformer Autoencoding with Prototype-Guided Mining for Open-World Object Detection / Applied Sciences 15(20) : 10918~

[journal] Bibi, M. / 2025 / An Auto-Annotation Approach for Object Detection and Depth-Based Distance Estimation in Security and Surveillance Systems / IEEE Access 13 : 45240~45251

[journal] Iqbal, Muhammad Ali / 2024 / Synthetic image generation using conditional GAN-provided single-sample face image / Applied Sciences 14(12) : 5049~

KJCKorea
Journal Central

Journal of Internet of Things and Convergence 2025 KCI Impact Factor : 0.75

Open-World Object Detection and Segmentation: Current Challenges and Emerging Opportunities

ABSTRACT

KEYWORDS

Journal Copyright Policy

Citation status

* References for papers published after 2025 are currently being built.

Journal of Internet of Things and Convergence 2025 KCI Impact Factor : 0.75

Open-World Object Detection and Segmentation: Current Challenges and Emerging Opportunities

ABSTRACT

KEYWORDS

Journal Copyright Policy

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (0)

REFERENCES (22) * References for papers published after 2025 are currently being built.

Search PDF

Citation

* References for papers published after 2025 are currently being built.