mlsanityData to 7 Oct 2026

Semi-Supervised Object Detection with Uncurated Unlabeled Data for Remote Sensing Images

arXiv 2310.05498 ↗First posted 9 Oct 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Annotating remote sensing images (RSIs) presents a notable challenge due to its labor-intensive nature. Semi-supervised object detection (SSOD) methods tackle this issue by generating pseudo-labels for the unlabeled data, assuming that all classes found in the unlabeled dataset are also represented in the labeled data. However, real-world situations introduce the possibility of out-of-distribution (OOD) samples being mixed with in-distribution (ID) samples within the unlabeled dataset. In this paper, we delve into techniques for conducting SSOD directly on uncurated unlabeled data, which is termed Open-Set Semi-Supervised Object Detection (OSSOD). Our approach commences by employing labeled in-distribution data to dynamically construct a class-wise feature bank (CFB) that captures features specific to each class. Subsequently, we compare the features of predicted object bounding boxes with the corresponding entries in the CFB to calculate OOD scores. We design an adaptive threshold based on the statistical properties of the CFB, allowing us to filter out OOD samples effectively. The effectiveness of our proposed method is substantiated through extensive experiments on two widely used remote sensing object detection datasets: DIOR and DOTA. These experiments showcase the superior performance and efficacy of our approach for OSSOD on RSIs.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 39 of its 65 references that are in the map. First posted on arXiv 9 Oct 2023.

Builds on

39 of 65 references.

References · 39

  1. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  3. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  4. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  5. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  6. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  7. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  8. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  9. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  10. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  11. 2019Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmarkcited by 339
  12. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
27 more
  1. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  2. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  3. 2021Instant-Teaching: An End-to-End Semi-Supervised Object Detection Frameworkcited by 112
  4. 2020Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learningcited by 82
  5. 2022Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectorscited by 69
  6. 2022PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detectioncited by 51
  7. 2022Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detectioncited by 48
  8. 2022Label Matching Semi-Supervised Object Detectioncited by 44
  9. 2022Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detectioncited by 43
  10. 2022H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detectioncited by 36
  11. 2022Dense Learning based Semi-Supervised Object Detectioncited by 32
  12. 2019Statistical Analysis of Nearest Neighbor Methods for Anomaly Detectioncited by 29
  13. 2023Semi-DETR: Semi-Supervised Object Detection with Detection Transformerscited by 27
  14. 2023IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilizationcited by 23
  15. 2023SOOD: Towards Semi-Supervised Oriented Object Detectioncited by 19
  16. 2022Open-Set Semi-Supervised Object Detectioncited by 17
  17. 2023Efficient Teacher: Semi-Supervised Object Detection for YOLOv5cited by 17
  18. 2023Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detectioncited by 14
  19. 2022Knowledge Distillation Meets Open-Set Semi-Supervised Learningcited by 8
  20. 2023Improving Open-Set Semi-Supervised Learning with Self-Supervisioncited by 6
  21. 2021Active learning for object detection in high-resolution satellite imagescited by 5
  22. 2023Revisiting Class Imbalance for End-to-end Semi-Supervised Object Detectioncited by 5
  23. 2023Few-shot Object Detection in Remote Sensing: Lifting the Curse of Incompletely Annotated Novel Objectscited by 5
  24. 2020Deep Active Learning for Remote Sensing Object Detectioncited by 3
  25. 2022Open-Set Semi-Supervised Learning for 3D Point Cloud Understandingcited by 3
  26. 2023Adaptive Negative Evidential Deep Learning for Open-set Semi-supervised Learningcited by 3
  27. 2023Exploration and Exploitation of Unlabeled Data for Open-Set Semi-Supervised Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 4.

4 papers.

  1. 2024PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Imagescited by 24
  2. 2024CLIP-Guided Source-Free Object Detection in Aerial Imagescited by 4
  3. 2024Diverse Teacher-Students for Deep Safe Semi-Supervised Learning under Class Mismatchcited by 0
  4. 2024Investigating Long-term Training for Remote Sensing Object Detectioncited by 0