mlsanityData to 7 Oct 2026

Towards Open-Set Object Detection and Discovery

arXiv 2204.05604 ↗First posted 12 Apr 2022cs.CVcited by 44

Not on the map. Why?

Abstract (arXiv)

With the human pursuit of knowledge, open-set object detection (OSOD) has been designed to identify unknown objects in a dynamic world. However, an issue with the current setting is that all the predicted unknown objects share the same category as "unknown", which require incremental learning via a human-in-the-loop approach to label novel classes. In order to address this problem, we present a new task, namely Open-Set Object Detection and Discovery (OSODD). This new task aims to extend the ability of open-set object detectors to further discover the categories of unknown objects based on their visual appearance without human effort. We propose a two-stage method that first uses an open-set object detector to predict both known and unknown objects. Then, we study the representation of predicted objects in an unsupervised manner and discover new categories from the set of unknown objects. With this method, a detector is able to detect objects belonging to known classes and define novel categories for objects of unknown classes with minimal supervision. We show the performance of our model on the MS-COCO dataset under a thorough evaluation protocol. We hope that our work will promote further research towards a more robust real-world detection system.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Builds on 40 of its 55 references that are in the map. First posted on arXiv 12 Apr 2022.

Builds on

40 of 55 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2017Mask R-CNNcited by 7,259
  9. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  10. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  11. 2015Fast R-CNNcited by 2,930
  12. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
28 more
  1. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  2. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  3. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  4. 2017Random Erasing Data Augmentationcited by 1,235
  5. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
  6. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  7. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  8. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  9. 2021Towards Open World Object Detectioncited by 297
  10. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  11. 2014Towards Open World Recognitioncited by 226
  12. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 223
  13. 2022Generalized Category Discoverycited by 209
  14. 2021A Unified Objective for Novel Class Discoverycited by 161
  15. 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 141
  16. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 119
  17. 2021AutoNovel: Automatically Discovering and Learning Novel Visual Categoriescited by 116
  18. 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
  19. 2021Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillationcited by 104
  20. 2019Efficient Parameter-free Clustering Using First Neighbor Relationscited by 96
  21. 2020OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open Worldcited by 93
  22. 2015Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposalscited by 69
  23. 2020Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNNcited by 61
  24. 2021Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Datacited by 55
  25. 2018Deep Object Co-Segmentationcited by 35
  26. 2022Revisiting Open World Object Detectioncited by 30
  27. 2021The Pursuit of Knowledge: Discovering and Localizing Novel Categories using Dual Memorycited by 13
  28. 2022GOSS: Towards Generalized Open-set Semantic Segmentationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 11; 2024: 13; 2025: 10; 2026: 5.

44 papers.

Sort:

By area:

  1. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  2. 2023Goal-Driven Explainable Clustering via Language Descriptionscited by 58
  3. 2024AIDE: An Automatic Data Engine for Object Detection in Autonomous Drivingcited by 26
  4. 2023Novel Class Discovery: an Introduction and Key Conceptscited by 24
  5. 2024Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detectioncited by 24
  6. 2023AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Datasetcited by 21
  7. 2022MOVE: Unsupervised Movable Object Segmentation and Detectioncited by 20
  8. 2024Happy: A Debiased Learning Framework for Continual Generalized Category Discoverycited by 18
  9. 2022Curved Geometric Networks for Visual Anomaly Recognitioncited by 15
  10. 2022PointCaM: Cut-and-Mix for Open-Set Point Cloud Learningcited by 11
  11. 2024Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modelingcited by 10
  12. 2022Towards Generalized Few-Shot Open-Set Object Detectioncited by 8
32 more
  1. 2024Mitigating Label Noise on Graph via Topological Sample Selectioncited by 6
  2. 2025Category Discovery: An Open-World Perspectivecited by 5
  3. 2025DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detectioncited by 5
  4. 2023USD: Unknown Sensitive Detector Empowered by Decoupled Objectness and Segment Anything Modelcited by 4
  5. 2023NOMAD: A Natural, Occluded, Multi-scale Aerial Dataset, for Emergency Response Scenarioscited by 4
  6. 2025SmokeBench: Evaluating Multimodal Large Language Models for Wildfire Smoke Detectioncited by 4
  7. 2024Spoof Diarization: "What Spoofed When" in Partially Spoofed Audiocited by 3
  8. 2025MedDCR: Learning to Design Agentic Workflows for Medical Codingcited by 3
  9. 2023A Practical Approach to Novel Class Discovery in Tabular Datacited by 2
  10. 2023OpenNet: Incremental Learning for Autonomous Driving Object Detection with Balanced Losscited by 2
  11. 2024PANDAS: Prototype-based Novel Class Discovery and Detectioncited by 2
  12. 2024UADet: A Remarkably Simple Yet Effective Uncertainty-Aware Open-Set Object Detection Frameworkcited by 2
  13. 2025Text Classification Under Class Distribution Shift: A Surveycited by 2
  14. 2022Rethinking Open-Set Object Detection: Issues, a New Formulation, and Taxonomycited by 1
  15. 2023Efficient Object Detection in Autonomous Driving using Spiking Neural Networks: Performance, Energy Consumption Analysis, and Insights into Open-set Object Discoverycited by 1
  16. 2024O1O: Grouping of Known Classes to Identify Unknown Objects as Odd-One-Outcited by 1
  17. 2025OW-CLIP: Data-Efficient Visual Supervision for Open-World Object Detection via Human-AI Collaborationcited by 1
  18. 2025FSP-DETR: Few-Shot Prototypical Parasitic Ova Detectioncited by 1
  19. 2023Partial-label Learning with Mixed Closed-set and Open-set Out-of-candidate Examplescited by 0
  20. 2023Open-Set Object Recognition Using Mechanical Properties During Interactioncited by 0
  21. 2024Wasserstein Distance-based Expansion of Low-Density Latent Regions for Unknown Class Detectioncited by 0
  22. 2024OW-Rep: Open World Object Detection with Instance Representation Learningcited by 0
  23. 2024Psych-Occlusion: Using Visual Psychophysics for Aerial Detection of Occluded Persons during Search and Rescuecited by 0
  24. 2024Unlocking the Potential of Weakly Labeled Data: A Co-Evolutionary Learning Framework for Abnormality Detection and Report Generationcited by 0
  25. 2025ADAM: Autonomous Discovery and Annotation Model using LLMs for Context-Aware Annotationscited by 0
  26. 2025OpenWildlife: Open-Vocabulary Multi-Species Wildlife Detector for Geographically-Diverse Aerial Imagerycited by 0
  27. 2025SonoVision: A Computer Vision Approach for Helping Visually Challenged Individuals Locate Objects with the Help of Sound Cuescited by 0
  28. 2026MOSLD-Bench: Multilingual Open-Set Learning and Discovery Benchmark for Text Categorizationcited by 0
  29. 2026Towards Adaptive Open-Set Object Detection via Category-Level Collaboration Knowledge Miningcited by 0
  30. 2026AusSmoke meets MultiNatSmoke: a fully-labelled diverse smoke segmentation datasetcited by 0
  31. 2026The Detector Teaches Itself: Lightweight Self-Supervised Adaptation for Open-Vocabulary Object Detectioncited by 0
  32. 2026LV-OSD: Language-Vision-Complementary Open-Set Object Detectioncited by 0