Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Semi-Supervised Object Detection with Uncurated Unlabeled Data for Remote Sensing Images (2310.05498v1)

Published 9 Oct 2023 in cs.CV

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (62)
  1. G. Cheng, Y. Si, H. Hong, X. Yao, and L. Guo, “Cross-scale feature fusion for object detection in optical remote sensing images,” IEEE Geoscience and Remote Sensing Letters, 2021.
  2. C. Zhang, K.-M. Lam, and Q. Wang, “Cof-net: A progressive coarse-to-fine framework for object detection in remote-sensing imagery,” IEEE Transactions on Geoscience and Remote Sensing, 2023.
  3. Y. Wu, K. Zhang, J. Wang, Y. Wang, Q. Wang, and X. Li, “Gcwnet: A global context-weaving network for object detection in remote sensing images,” IEEE Transactions on Geoscience and Remote Sensing, 2022.
  4. Y. Han, W. Meng, W. Tang, and L. Tang, “Capsule-inferenced object detection for remote sensing images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023.
  5. N. Liu, T. Celik, T. Zhao, C. Zhang, and H.-C. Li, “Afdet: Toward more accurate and faster object detection in remote sensing images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021.
  6. Y. Ma, L. Chai, and L. Jin, “Scale decoupled pyramid for object detection in aerial images,” IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–14, 2023.
  7. N. Liu, T. Celik, and H.-C. Li, “Gated ladder-shaped feature pyramid network for object detection in optical remote sensing images,” IEEE Geoscience and Remote Sensing Letters, 2022.
  8. Z. Zhang, Z. Feng, and S. Yang, “Semi-supervised object detection framework with object first mixup for remote sensing images,” in IEEE International Geoscience and Remote Sensing Symposium, 2021.
  9. G. Chen, L. Liu, W. Hu, and Z. Pan, “Semi-supervised object detection in remote sensing images using generative adversarial networks,” in IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, 2018, pp. 2503–2506.
  10. W. Hua, D. Liang, J. Li, X. Liu, Z. Zou, X. Ye, and X. Bai, “Sood: Towards semi-supervised oriented object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 15 558–15 567.
  11. Y.-C. Liu, C.-Y. Ma, X. Dai, J. Tian, P. Vajda, Z. He, and Z. Kira, “Open-set semi-supervised object detection,” in European Conference on Computer Vision, 2022.
  12. Z. Wang, L. Xiao, L. Xiang, Z. Weng, and T. Yamasaki, “Online open-set semi-supervised object detection by valuable instances mining,” 2023.
  13. D. Hendrycks, M. Mazeika, and T. Dietterich, “Deep anomaly detection with outlier exposure,” in International Conference on Learning Representations, 2019.
  14. Y.-C. Hsu, Y. Shen, H. Jin, and Z. Kira, “Generalized odin: Detecting out-of-distribution image without learning from out-of-distribution data,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.
  15. K. Lee, K. Lee, H. Lee, and J. Shin, “A simple unified framework for detecting out-of-distribution samples and adversarial attacks,” Advances in neural information processing systems, 2018.
  16. M. Caron, H. Touvron, I. Misra, H. Jégou, J. Mairal, P. Bojanowski, and A. Joulin, “Emerging properties in self-supervised vision transformers,” in Proceedings of the International Conference on Computer Vision, 2021.
  17. K. Roth, L. Pemula, J. Zepeda, B. Schölkopf, T. Brox, and P. Gehler, “Towards total recall in industrial anomaly detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022.
  18. C.-L. Li, K. Sohn, J. Yoon, and T. Pfister, “Cutpaste: Self-supervised learning for anomaly detection and localization,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021.
  19. Y. Zhou, X. Jiang, Z. Chen, L. Chen, and X. Liu, “A semisupervised arbitrary-oriented sar ship detection network based on interference consistency learning and pseudolabel calibration,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 5893–5904, 2023.
  20. X. Feng, X. Yao, G. Cheng, and J. Han, “Weakly supervised rotation-invariant aerial object detection network,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 14 146–14 155.
  21. X. Yang, G. Zhang, W. Li, Y. Zhou, X. Wang, and J. Yan, “H2rbox: Horizontal box annotation is all you need for oriented object detection,” in The Eleventh International Conference on Learning Representations, 2022.
  22. Z. Tan, Z. Jiang, C. Guo, and H. Zhang, “Wsodet: A weakly supervised oriented detector for aerial object detection,” IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–12, 2023.
  23. Y. Yu, X. Yang, Q. Li, Y. Zhou, G. Zhang, J. Yan, and F. Da, “H2rbox-v2: Boosting hbox-supervised oriented object detection via symmetric learning,” arXiv preprint arXiv:2304.04403, 2023.
  24. G. Wang, X. Zhang, Z. Peng, X. Jia, X. Tang, and L. Jiao, “Mol: Towards accurate weakly supervised remote sensing object detection via multi-view noisy learning,” ISPRS Journal of Photogrammetry and Remote Sensing, 2023.
  25. G. Cheng, B. Yan, P. Shi, K. Li, X. Yao, L. Guo, and J. Han, “Prototype-cnn for few-shot object detection in remote sensing images,” IEEE Transactions on Geoscience and Remote Sensing, 2022.
  26. N. Liu, X. Xu, T. Celik, Z. Gan, and H.-C. Li, “Transformation-invariant network for few-shot object detection in remote sensing images,” arXiv preprint arXiv:2303.06817, 2023.
  27. X. Lu, X. Sun, W. Diao, Y. Mao, J. Li, Y. Zhang, P. Wang, and K. Fu, “Few-shot object detection in aerial imagery guided by text-modal knowledge,” IEEE Transactions on Geoscience and Remote Sensing, 2023.
  28. T. Zhang, X. Zhang, P. Zhu, X. Jia, X. Tang, and L. Jiao, “Generalized few-shot object detection in remote sensing images,” ISPRS Journal of Photogrammetry and Remote Sensing, 2023.
  29. F. Zhang, Y. Shi, Z. Xiong, and X. X. Zhu, “Few-shot object detection in remote sensing: Lifting the curse of incompletely annotated novel objects,” arXiv preprint arXiv:2309.10588, 2023.
  30. B. Wang, G. Ma, H. Sui, Y. Zhang, H. Zhang, and Y. Zhou, “Few-shot object detection in remote sensing imagery via fuse context dependencies and global features,” Remote Sensing, vol. 15, no. 14, p. 3462, 2023.
  31. Z. Qu, J. Du, Y. Cao, Q. Guan, and P. Zhao, “Deep active learning for remote sensing object detection,” arXiv preprint arXiv:2003.08793, 2020.
  32. A. Goupilleau, T. Ceillier, and M.-C. Corbineau, “Active learning for object detection in high-resolution satellite images,” in Conference on Artificial Intelligence for Defense, 2020.
  33. K. Uehara, H. Nosato, M. Murakawa, and H. Sakanashi, “Object detection in satellite images based on active learning utilizing visual explanation,” in 2019 11th International Symposium on Image and Signal Processing and Analysis (ISPA).   IEEE, 2019, pp. 27–31.
  34. K. Sohn, Z. Zhang, C.-L. Li, H. Zhang, C.-Y. Lee, and T. Pfister, “A simple semi-supervised learning framework for object detection,” arXiv preprint arXiv:2005.04757, 2020.
  35. Q. Zhou, C. Yu, Z. Wang, Q. Qian, and H. Li, “Instant-teaching: An end-to-end semi-supervised object detection framework,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 4081–4090.
  36. Y.-C. Liu, C.-Y. Ma, Z. He, C.-W. Kuo, K. Chen, P. Zhang, B. Wu, Z. Kira, and P. Vajda, “Unbiased teacher for semi-supervised object detection,” in International Conference on Learning Representations, 2021.
  37. M. Xu, Z. Zhang, H. Hu, J. Wang, L. Wang, F. Wei, X. Bai, and Z. Liu, “End-to-end semi-supervised object detection with soft teacher,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021.
  38. B. Chen, W. Chen, S. Yang, Y. Xuan, J. Song, D. Xie, S. Pu, M. Song, and Y. Zhuang, “Label matching semi-supervised object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 14 381–14 390.
  39. G. Li, X. Li, Y. Wang, Y. Wu, D. Liang, and S. Zhang, “Pseco: Pseudo labeling and consistency training for semi-supervised object detection,” in European Conference on Computer Vision, 2022.
  40. X. Wang, X. Yang, S. Zhang, Y. Li, L. Feng, S. Fang, C. Lyu, K. Chen, and W. Zhang, “Consistent-teacher: Towards reducing inconsistent pseudo-targets in semi-supervised object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 3240–3249.
  41. P. Kar, V. Chudasama, N. Onoe, and P. Wasnik, “Revisiting class imbalance for end-to-end semi-supervised object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 4569–4578.
  42. B. Chen, P. Li, X. Chen, B. Wang, L. Zhang, and X.-S. Hua, “Dense learning based semi-supervised object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022.
  43. Y.-C. Liu, C.-Y. Ma, and Z. Kira, “Unbiased teacher v2: Semi-supervised object detection for anchor-free and anchor-based detectors,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9819–9828.
  44. H. Zhou, Z. Ge, S. Liu, W. Mao, Z. Li, H. Yu, and J. Sun, “Dense teacher: Dense pseudo-labels for semi-supervised object detection,” in Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part IX.   Springer, 2022, pp. 35–50.
  45. B. Xu, M. Chen, W. Guan, and L. Hu, “Efficient teacher: Semi-supervised object detection for yolov5,” arXiv preprint arXiv:2302.07577, 2023.
  46. C. Liu, W. Zhang, X. Lin, W. Zhang, X. Tan, J. Han, X. Li, E. Ding, and J. Wang, “Ambiguity-resistant semi-supervised learning for dense object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 15 579–15 588.
  47. J. Zhang, X. Lin, W. Zhang, K. Wang, X. Tan, J. Han, E. Ding, J. Wang, and G. Li, “Semi-detr: Semi-supervised object detection with detection transformers,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 23 809–23 818.
  48. X. Shi, X. Xu, W. Zhang, X. Zhu, C. S. Foo, and K. Jia, “Open-set semi-supervised learning for 3d point cloud understanding,” in 2022 26th International Conference on Pattern Recognition (ICPR), 2022.
  49. Q. Yu, D. Ikami, G. Irie, and K. Aizawa, “Multi-task curriculum framework for open-set semi-supervised learning,” in European Conference on Computer Vision, 2020.
  50. K. Saito, D. Kim, and K. Saenko, “Openmatch: Open-set semi-supervised learning with open-set consistency regularization,” Advances in Neural Information Processing Systems, 2021.
  51. Y. Chen, X. Zhu, W. Li, and S. Gong, “Semi-supervised learning under class distribution mismatch,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2020.
  52. Y. Yu, D. Deng, F. Liu, Y. Jin, Q. Dou, G. Chen, and P.-A. Heng, “Adaptive negative evidential deep learning for open-set semi-supervised learning,” arXiv preprint arXiv:2303.12091, 2023.
  53. J. Yang, X. Zhu, A. Bulat, B. Martinez, and G. Tzimiropoulos, “Knowledge distillation meets open-set semi-supervised learning,” arXiv preprint arXiv:2205.06701, 2022.
  54. E. Wallin, L. Svensson, F. Kahl, and L. Hammarstrand, “Improving open-set semi-supervised learning with self-supervision,” arXiv preprint arXiv:2301.10127, 2023.
  55. Z. Li, L. Qi, Y. Shi, and Y. Gao, “Iomatch: Simplifying open-set semi-supervised learning with joint inliers and outliers utilization,” arXiv preprint arXiv:2308.13168, 2023.
  56. G. Zhao, G. Li, Y. Qin, J. Zhang, Z. Chai, X. Wei, L. Lin, and Y. Yu, “Exploration and exploitation of unlabeled data for open-set semi-supervised learning,” arXiv preprint arXiv:2306.17699, 2023.
  57. X. Gu, L. Akoglu, and A. Rinaldo, “Statistical analysis of nearest neighbor methods for anomaly detection,” Advances in Neural Information Processing Systems, 2019.
  58. K. Li, G. Wan, G. Cheng, L. Meng, and J. Han, “Object detection in optical remote sensing images: A survey and a new benchmark,” ISPRS Journal of Photogrammetry and Remote Sensing, 2020.
  59. G.-S. Xia, X. Bai, J. Ding, Z. Zhu, S. Belongie, J. Luo, M. Datcu, M. Pelillo, and L. Zhang, “Dota: A large-scale dataset for object detection in aerial images,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018.
  60. D. Hendrycks and K. Gimpel, “A baseline for detecting misclassified and out-of-distribution examples in neural networks,” in International Conference on Learning Representations, 2016.
  61. W. Liu, X. Wang, J. Owens, and Y. Li, “Energy-based out-of-distribution detection,” Advances in neural information processing systems, 2020.
  62. K. Chen, J. Wang, J. Pang, Y. Cao, Y. Xiong, X. Li, S. Sun, W. Feng, Z. Liu, J. Xu, Z. Zhang, D. Cheng, C. Zhu, T. Cheng, Q. Zhao, B. Li, X. Lu, R. Zhu, Y. Wu, J. Dai, J. Wang, J. Shi, W. Ouyang, C. C. Loy, and D. Lin, “MMDetection: Open mmlab detection toolbox and benchmark,” arXiv preprint arXiv:1906.07155, 2019.
Citations (7)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now