mlsanityData to 14 Oct 2026

Open-Set Semi-Supervised Object Detection

arXiv 2208.13722 ↗First posted 29 Aug 2022cs.CV cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Recent developments for Semi-Supervised Object Detection (SSOD) have shown the promise of leveraging unlabeled data to improve an object detector. However, thus far these methods have assumed that the unlabeled data does not contain out-of-distribution (OOD) classes, which is unrealistic with larger-scale unlabeled datasets. In this paper, we consider a more practical yet challenging problem, Open-Set Semi-Supervised Object Detection (OSSOD). We first find the existing SSOD method obtains a lower performance gain in open-set conditions, and this is caused by the semantic expansion, where the distracting OOD objects are mispredicted as in-distribution pseudo-labels for the semi-supervised training. To address this problem, we consider online and offline OOD detection modules, which are integrated with SSOD methods. With the extensive studies, we found that leveraging an offline OOD detector based on a self-supervised vision transformer performs favorably against online OOD detectors due to its robustness to the interference of pseudo-labeling. In the experiment, our proposed framework effectively addresses the semantic expansion issue and shows consistent improvements on many OSSOD benchmarks, including large-scale COCO-OpenImages. We also verify the effectiveness of our framework under different OSSOD conditions, including varying numbers of in-distribution classes, different degrees of supervision, and different combinations of unlabeled sets.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 50 of its 58 references that are in the map. First posted on arXiv 29 Aug 2022.

Builds on

50 of 58 references.

References · 50

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  9. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  10. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  12. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
38 more
  1. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  3. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  4. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  5. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  6. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 906
  7. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  8. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 614
  9. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 569
  10. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  11. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  12. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  13. 2020Open-Vocabulary Object Detection Using Captionscited by 427
  14. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  15. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 316
  16. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 306
  17. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  18. 2021Towards Open World Object Detectioncited by 297
  19. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  20. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  21. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  22. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  23. 2018MixUp as Locally Linear Out-Of-Manifold Regularizationcited by 158
  24. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 116
  25. 2021Instant-Teaching: An End-to-End Semi-Supervised Object Detection Frameworkcited by 113
  26. 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
  27. 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
  28. 2021Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labelingcited by 84
  29. 2020Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learningcited by 82
  30. 2021Towards Discovery and Attribution of Open-world GAN Generated Imagescited by 66
  31. 2020Proposal Learning for Semi-Supervised Object Detectioncited by 55
  32. 2021OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outlierscited by 43
  33. 2019Soft Anchor-Point Object Detectioncited by 42
  34. 2021Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learningcited by 40
  35. 2021Learning to Detect Every Thing in an Open Worldcited by 37
  36. 2021Uncertainty for Identifying Open-Set Errors in Visual Object Detectioncited by 26
  37. 2021An Effective Baseline for Robustness to Distributional Shiftcited by 25
  38. 2021A Geometric Perspective towards Neural Calibration via Sensitivity Decompositioncited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 9; 2024: 5; 2025: 2; 2026: 1.

17 papers.

Sort:

By area:

  1. 2023OtterHD: A High-Resolution Multi-modality Modelcited by 72
  2. 2024AIDE: An Automatic Data Engine for Object Detection in Autonomous Drivingcited by 26
  3. 2023Label-Efficient Learning in Agriculture: A Comprehensive Reviewcited by 16
  4. 2024Open-Set Recognition in the Age of Vision-Language Modelscited by 13
  5. 2023RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Datacited by 10
  6. 2023Unsupervised Recognition of Unknown Objects for Open-World Object Detectioncited by 6
  7. 2023Semi-supervised Object Detection: A Survey on Recent Research and Progresscited by 5
  8. 2025Distracted Robot: How Visual Clutter Undermine Robotic Manipulationcited by 5
  9. 2023Semi-Supervised Object Detection with Uncurated Unlabeled Data for Remote Sensing Imagescited by 4
  10. 2024Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformercited by 4
  11. 2025Improving Robotic Manipulation Robustness via NICE Scene Surgerycited by 3
  12. 2023Open-World Weakly-Supervised Object Localizationcited by 2
5 more
  1. 2023Generalized Open-World Semi-Supervised Object Detectioncited by 1
  2. 2023Online Open-set Semi-supervised Object Detection with Dual Competing Headcited by 0
  3. 2024Multimodal-Enhanced Objectness Learner for Corner Case Detection in Autonomous Drivingcited by 0
  4. 2024Class-balanced Open-set Semi-supervised Object Detection for Medical Imagescited by 0
  5. 2026HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Imagescited by 0