Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 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: A Survey on Recent Research and Progress (2306.14106v1)

Published 25 Jun 2023 in cs.CV and cs.AI

Abstract: In recent years, deep learning technology has been maturely applied in the field of object detection, and most algorithms tend to be supervised learning. However, a large amount of labeled data requires high costs of human resources, which brings about low efficiency and limitations. Semi-supervised object detection (SSOD) has been paid more and more attentions due to its high research value and practicability. It is designed to learn information by using small amounts of labeled data and large amounts of unlabeled data. In this paper, we present a comprehensive and up-to-date survey on the SSOD approaches from five aspects. We first briefly introduce several ways of data augmentation. Then, we dive the mainstream semi-supervised strategies into pseudo labels, consistent regularization, graph based and transfer learning based methods, and introduce some methods in challenging settings. We further present widely-used loss functions, and then we outline the common benchmark datasets and compare the accuracy among different representative approaches. Finally, we conclude this paper and present some promising research directions for the future. Our survey aims to provide researchers and practitioners new to the field as well as more advanced readers with a solid understanding of the main approaches developed over the past few years.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (59)
  1. L. Liu, W. Ouyang, X. Wang, P. Fieguth, J. Chen, X. Liu, and M. Pietikainen, “Deep learning for generic object detection: A survey,” International Journal of Computer Vision., vol. 128, pp. 261–318, Feb. 2020.
  2. L. Jiao, F. Zhang, F. Liu, S. Yang, L. Li, Z. Feng, and R. Qu, “A survey of deep learning-based object detection,” IEEE Access., vol. 7, pp. 128837–128868, Sep. 2019.
  3. S. Zaidi, M. Ansari, A. Aslam, N. Kanwal, M. Asghar, and Brian Lee, “A survey of modern deep learning based object detection models,” Digital Signal Processing., vol. 126, pp. 103514, Jun. 2022.
  4. S. Ding, Z. Zhu, and X. Zhang, “An overview on semi-supervised support vector machine,” Neural Computing & Applications., vol. 28, pp. 969–978, May. 2017.
  5. J.van Engelen, H. Hoos, “A survey on semi-supervised learning,” Machine Learning., vol. 109, pp. 373–440, Feb. 2020.
  6. X. Yang, Z. Song, I. King and Z. Xu, “A Survey on Deep Semi-Supervised Learning,” IEEE Transactions on Knowledge and Data Engineering., pp. 1–20, Nov. 2022.
  7. A. Oliver, A. Odena, C. Raffel, E. D. Cubuk, and I. J. Goodfellow, “Realistic Evaluation of Deep Semi-Supervised Learning Algorithms,” in Neural Information Processing Systems, NY, USA, 2018, pp. 3239–3250.
  8. Y. Ouali, C. Hudelot, and M. Tami, “An Overview of Deep Semi-Supervised Learning,” arXiv abs/2006.05278, 2020.
  9. C. Li, K. Xu, J. Zhu, and B. Zhang, “Triple generative adversarial nets,” in Neural Information Processing Systems, California, USA, 2017, pp. 4091–4101.
  10. E. Abbasnejad, A. Dick, and A. den Hengel, “Infinite variational autoencoder for semi-supervised learning,” in In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017, pp. 781–790.
  11. W. Hamilton, Z. Ying, and J. Leskovec, “Inductive representation learning on large graphs,” in Neural Information Processing Systems, California, USA, 2017, pp. 1025–1035.
  12. Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, and S. Philip, “A comprehensive survey on graph neural networks,” IEEE Transactions on Neural Networks and Learning Systems., vol. 32, pp. 4–24, Jan. 2021.
  13. T. Miyato, S. Maeda, M. Koyama, and S. Ishii, “Virtual adversarial training: a regularization method for supervised and semi-supervised learning,” IEEE transactions on pattern analysis and machine intelligence., vol. 41, pp. 1979–1993, Aug. 2018.
  14. A. Tarvainen and H. Valpola, “Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results,” in Neural Information Processing Systems, California, USA, 2017, pp. 1195–1204.
  15. X. Zhai, A. Oliver, A. Kolesnikov, and L. Beyer, “S4l: Self-supervised semi-supervised learning,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea(South), 2019, pp. 1476–1485.
  16. Y. Zou, Z. Yu, X. Liu, B. Vijaya Kumar, and J. Wang, “Confidence regularized self-training,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea(South), 2019, pp. 5981–5990.
  17. C. Wei, K. Sohn, C. Mellina, A. Yuille, and F. Yang, “Crest: A class-rebalancing self-training framework for imbalanced semi-supervised learning,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 2021, pp. 10852–10861.
  18. X. Wang, D. Kihara, J. Luo, and G. Qi, “EnAET: A self-trained framework for semi-supervised and supervised learning with ensemble transformations,” IEEE Transactions on Image Processing., vol. 30, pp. 1639–1647, Jan. 2021.
  19. D. Berthelot, N. Carlini, I. Goodfellow, N. Papernot, A. Oliver, and C. Raffel, “Mixmatch: A holistic approach to semi-supervised learning,” in Advances in neural information processing systems, Vancouver, BC, Canada, 2019, pp. 5049–5059.
  20. C. Kuo, C. Ma, J. Huang, Z. Kira, G. Tech, and V. Tech, “FeatMatch: Feature-based augmentation for semi-supervised learning,” in European Conference on Computer Vision, Glasgow, UK, 2020, pp. 479–495.
  21. K. Sohn, D. Berthelot, C. Li, Z. Zhang, N. Carlini, E. Cubuk, A. Kurakin, H. Zhang, and C. Raffel, “FixMatch: Simplifying semi-supervised learning with consistency and confidence,” in Advances in neural information processing systems, California, USA, 2020, pp. 596–608.
  22. B. Chen, P. Li, X. Chen, B. Wang, L. Zhang, and X. Hua, “Dense Learning based Semi-Supervised Object Detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 2022, pp. 4805–4814.
  23. F. Zhang, T. Pan, and B. Wang, “Semi-supervised object detection with adaptive class-rebalancing self-training,” in Proceedings of the AAAI Conference on Artificial Intelligence, Palo Alto, California, USA, 2022, pp. 3252–3261.
  24. 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, Palo Alto, California, USA, 2021, pp. 4081–4090.
  25. J. Kim, J. Jang, S. Seo, J. Jeong, J. Na, and N. Kwak, “MUM: Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 2022, pp. 14492–14501.
  26. K. Sohn, Z. Zhang, C. Li, H. Zhang, C. Lee, and T. Pfister, “A simple semi-supervised learning framework for object detection,” arXiv preprint arXiv:2005.04757, 2020.
  27. B. Zoph, G. Ghiasi, T. Lin, Y. Cui, H. Liu, E. Cubuk, and Q. Le, “Rethinking pre-training and self-training,” in Advances in neural information processing systems, Vancouver, BC, Canada, 2020, pp. 3833–3845.
  28. Q. Yang, X. Wei, B. Wang, X. Hua, and L. Zhang, “Interactive self-training with mean teachers for semi-supervised object detection,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Nashville, TN, USA, 2021, pp. 5937–5946.
  29. I. Radosavovic, P. Dollar, R. Girshick, G. Gkioxari, and K. He, “Data distillation: Towards omni-supervised learning,” in Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, USA, 2018, pp. 4119–4128.
  30. 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, Montreal, QC, Canada, 2021, pp. 3040–3049.
  31. Y. Liu, C. Ma, Z. He, C. 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.
  32. H. Li, Z. Wu, A. Shrivastava, and L. Davis, “Rethinking pseudo labels for semi-supervised object detection,” in Proceedings of the AAAI Conference on Artificial Intelligence, Palo Alto, California, USA, 2022, pp. 1314–1322.
  33. H. Li, X. Pan, K. Yan, F. Tang, and W. Zheng, “SIOD: Single Instance Annotated Per Category Per Image for Object Detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 2022, pp. 14177–14186.
  34. C. Ma, X. Pan, Q. Ye, F. Tang, W. Dong, and C. Xu, “CrossRectify: Leveraging Disagreement for Semi-supervised Object Detection,” Pattern Recognition., vol. 137, pp. 109280, Jan. 2022.
  35. 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, New Orleans, LA, USA, 2022, pp. 14361–14370.
  36. J. Guo, K. Han, H. Wu, C. Zhang, X. Chen, C. Xu and Y. Wang, “Positive-Unlabeled Data Purification in the Wild for Object Detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 2022, pp. 14177–14186.
  37. Y. Tang, W. Chen, Y. Luo, and Y. Zhang, “Humble teachers teach better students for semi-supervised object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 2021, pp. 2652–2661.
  38. 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 European Conference on Computer Vision, Tel Aviv, Israel, 2022, pp. 35–50.
  39. G. Li, X. Li, Y. Wang, Y. Wu, D. Liang, and S. Zhang, “DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection,” in Conference and Workshop on Neural Information Processing Systems, 2022.
  40. P. Wang, Z. Cai, H. Yang, G. Swaminathan, N. Vasconcelos, B. Schiele, and S. Soatto, “Omni-DETR: Omni-Supervised Object Detection with Transformers,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 2022, pp. 9357–9366.
  41. L. Chen, T. Yang, X. Zhang, W. Zhang, and J. Sun, “Points as queries: Weakly semi-supervised object de-tection by points,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 2021, pp. 8819–8828.
  42. S. Zhang, Z. Y, L. Liu, X. Wang, A. Zhou, and K. Chen, “Group R-CNN for Weakly Semi-supervised Object Detection with Points,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, 2022, pp. 9407–9416.
  43. Z. Wang, Y. Li, Y. Guo, L. Fang, and S. Wang, “Data-uncertainty guided multi-phase learning for semi-supervised object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 2021, pp. 4566–4575.
  44. Z. Wang, Y. Li, Y. Guo, and S. Wang, “Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification,” in Advances in Neural Information Processing Systems, 2021.
  45. L. Rossi, A. Karimi, and A. Prati, “Improving Localization for Semi-Supervised Object Detection,” in International Conference on Image Analysis and Processing, Lecce, Italy, 2022, pp. 516–527.
  46. S. Zhao, Z. Zhang, S. Schulter, L. Zhao, V. B.G, A. Stathopoulos, M. Chandraker, and D. Metaxas, “Exploiting unlabeled data with vision and language models for object detection,” in European Conference on Computer Vision, Tel Aviv, Israel, 2022, pp. 159–175.
  47. C. Feng, Y. Zhong, Z. Jie, X. Chu, H. Ren, X. Wei, W. Xie, and L. Ma, “Promptdet: Towards open-vocabulary detection using uncurated images,” in European Conference on Computer Vision, Tel Aviv, Israel, 2022, pp. 701–717.
  48. J. Jeong, S. Lee, J. Kim, and N. Kwak, “Consistency-based semi-supervised learning for object detection,” in Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, BC, Canada, 2019, pp. 10759–10768.
  49. G. Li, X. Li, Y. Wang, and Y. Wu, “PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection,” in European Conference on Computer Vision, Tel Aviv, Israel, 2022, pp. 457–472.
  50. J. Jeong, V. Verma, M. Hyun, J. nala, and N. Kwak, “Interpolation-based Semi-supervised Learning for Object Detection,” in Computer Vision and Pattern Recognition, Nashville, TN, USA, 2021, pp. 11597–11606.
  51. C. Chen, S. Dong, Y. Tian, K. Cao, L. Liu, and Y. Guo, “Temporal self-ensembling teacher for semi-supervised object detection,” IEEE Transactions on Multimedia., vol. 24, pp. 3679–3692, Aug. 2021.
  52. S. Ren, K. He, R. Girshick, and J. Sun, “ Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence., vol. 39, pp. 1137–1149, Jun. 2017.
  53. M. Dun, X. Chang-feng, L. Tie-bing, and H. Ao-ling, “ Graph-based semi-supervised learning for object tracking,” Systems Engineering and Electronics., Feb. 2016.
  54. J. Hoffman, S. Guadarrama, E. Tzeng, R. Hu, J. Donahue, R. Girshick, T. Darrell, and K. Saenko, “LSDA: Large scale detection through adaptation.,” in Neural Information Processing Systems, 2014.
  55. J. Gao, J Wang, S. Dai, L. Li, and R. Nevatia, “Note-rcnn: Noise tolerant ensemble rcnn for semi-supervised object detection,” in In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea(South), 2019, pp. 9507–9516.
  56. Y. Tang, J. Wang, B. Gao, E. Dellandréa, R. Gaizauskas and L. Chen, “Large Scale Semi-Supervised Object Detection Using Visual and Semantic Knowledge Transfer,” in Conference on Computer Vision and Pattern Recognition , Las Vegas, NV, USA, 2016, pp. 2119–2128.
  57. C. Chen, K. Debattista, and J. Han, “Semi-supervised object detection via virtual category learning,” in Lecture Notes in Computer Science, Springer, Cham, 2022, pp. 169–185.
  58. Y. Liu, C. Ma, X. Dai, J. Tian, P. Vajda, Z. He, and Z. Kira, “Open-Set Semi-Supervised Object Detection,” in In Proceedings of the IEEE/CVF International Conference on Computer Vision, Springer, Cham, 2022, pp. 143–159.
  59. B. Liu, H. Li, H. Kang, N. Vasconcelos,and G. Hua, “Semi-supervised long-tailed recognition using alternate sampling,” in International Conference on Learning Representations, 2022.
Citations (5)
View on Semantic Scholar

Summary

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

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