Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey (2403.01909v2)

Published 4 Mar 2024 in cs.CV and cs.AI

Abstract: Semantic segmentation is an important and popular research area in computer vision that focuses on classifying pixels in an image based on their semantics. However, supervised deep learning requires large amounts of data to train models and the process of labeling images pixel by pixel is time-consuming and laborious. This review aims to provide a first comprehensive and organized overview of the state-of-the-art research results on pseudo-label methods in the field of semi-supervised semantic segmentation, which we categorize from different perspectives and present specific methods for specific application areas. In addition, we explore the application of pseudo-label technology in medical and remote-sensing image segmentation. Finally, we also propose some feasible future research directions to address the existing challenges.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. Bidirectional copy-paste for semi-supervised medical image segmentation. In CVPR, pages 11514–11524, 2023.
  2. Semi-supervised semantic segmentation with cross pseudo supervision. In CVPR, pages 2613–2622, 2021.
  3. Debiased self-training for semi-supervised learning. NeurIPS, 35:32424–32437, 2022.
  4. Semi-supervised semantic segmentation with region relevance. arXiv:2304.11539, 2023.
  5. The cityscapes dataset for semantic urban scene understanding. In CVPR, pages 3213–3223, 2016.
  6. Semi-supervised semantic segmentation of remote sensing images based on dual cross-entropy consistency. Entropy, 25(4):681, 2023.
  7. The pascal visual object classes challenge: A retrospective. IJCV, 111:98–136, 2015.
  8. Ucc: Uncertainty guided cross-head co-training for semi-supervised semantic segmentation. In CVPR, pages 9947–9956, 2022.
  9. Conservative-progressive collaborative learning for semi-supervised semantic segmentation. TIP, 2023.
  10. Dmt: Dynamic mutual training for semi-supervised learning. PR, 130:108777, 2022.
  11. n-cps: Generalising cross pseudo supervision to n networks for semi-supervised semantic segmentation. arXiv:2112.07528, 2021.
  12. Are we ready for autonomous driving? the kitti vision benchmark suite. In CVPR, pages 3354–3361. IEEE, 2012.
  13. xbd: A dataset for assessing building damage from satellite imagery. arXiv:1911.09296, 2019.
  14. Re-distributing biased pseudo labels for semi-supervised semantic segmentation: A baseline investigation. In ICCV, pages 6930–6940, 2021.
  15. Atso: Asynchronous teacher-student optimization for semi-supervised image segmentation. In CVPR, pages 1235–1244, 2021.
  16. Kvasir-seg: A segmented polyp dataset. In MMM, pages 451–462. Springer, 2020.
  17. Semi-supervised semantic segmentation via gentle teaching assistant. NeurIPS, 35:2803–2816, 2022.
  18. Cafs: Class adaptive framework for semi-supervised semantic segmentation. arXiv:2303.11606, 2023.
  19. A three-stage self-training framework for semi-supervised semantic segmentation. TIP, 31:1805–1815, 2022.
  20. Segment anything. arXiv:2304.02643, 2023.
  21. Pruning-guided curriculum learning for semi-supervised semantic segmentation. In WACV, pages 5914–5923, 2023.
  22. Semi-supervised semantic segmentation with error localization network. In CVPR, pages 9957–9967, 2022.
  23. Dong-Hyun Lee et al. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML, volume 3, page 896. Atlanta, 2013.
  24. Saliency as pseudo-pixel supervision for weakly and semi-supervised semantic segmentation. TPAMI, 2023.
  25. A residual correction approach for semi-supervised semantic segmentation. In PRCV, pages 90–102. Springer, 2021.
  26. Semi-supervised remote sensing image semantic segmentation method based on deep learning. Electronics, 12(2):348, 2023.
  27. Pseudo labels for unsupervised domain adaptation: A review. Electronics, 12(15):3325, 2023.
  28. Microsoft coco: Common objects in context. In ECCV, pages 740–755. Springer, 2014.
  29. Perturbed and strict mean teachers for semi-supervised semantic segmentation. In CVPR, pages 4258–4267, 2022.
  30. The multimodal brain tumor image segmentation benchmark (brats). TMI, 34(10):1993–2024, 2014.
  31. A survey on semi-supervised semantic segmentation. arXiv:2302.09899, 2023.
  32. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. NeurIPS, 30, 2017.
  33. The gist and rist of iterative self-training for semi-supervised segmentation. In CRV, pages 58–66. IEEE, 2022.
  34. Land-cover classification with high-resolution remote sensing images using transferable deep models. Remote Sensing of Environment, 237:111322, 2020.
  35. Guidedmix-net: Semi-supervised semantic segmentation by using labeled images as reference. In AAAI, volume 36, pages 2379–2387, 2022.
  36. Satellite remote sensing identification of discolored standing trees for pine wilt disease based on semi-supervised deep learning. Remote Sensing, 14(23):5936, 2022.
  37. Card: Semi-supervised semantic segmentation via class-agnostic relation based denoising. In IJCAI, pages 1451–1457, 2022.
  38. Learning pseudo labels for semi-and-weakly supervised semantic segmentation. PR, 132:108925, 2022.
  39. Conflict-based cross-view consistency for semi-supervised semantic segmentation. In CVPR, pages 19585–19595, 2023.
  40. isaid: A large-scale dataset for instance segmentation in aerial images. In CVPR Workshops, pages 28–37, 2019.
  41. Querying labeled for unlabeled: Cross-image semantic consistency guided semi-supervised semantic segmentation. TPAMI, 2023.
  42. A global benchmark of algorithms for segmenting the left atrium from late gadolinium-enhanced cardiac magnetic resonance imaging. MEDIA, 67:101832, 2021.
  43. St++: Make self-training work better for semi-supervised semantic segmentation. In CVPR, pages 4268–4277, 2022.
  44. David Yarowsky. Unsupervised word sense disambiguation rivaling supervised methods. In ACL, pages 189–196, 1995.
  45. Learning from pixel-level label noise: A new perspective for semi-supervised semantic segmentation. TIP, 31:623–635, 2021.
  46. Deep mutual learning. In CVPR, pages 4320–4328, 2018.
  47. Semi-supervised semantic segmentation with uncertainty-guided self cross supervision. In ACCV, pages 4631–4647, 2022.
  48. Scene parsing through ade20k dataset. In CVPR, pages 633–641, 2017.
  49. C3-semiseg: Contrastive semi-supervised segmentation via cross-set learning and dynamic class-balancing. In ICCV, pages 7036–7045, 2021.
  50. Catastrophic forgetting problem in semi-supervised semantic segmentation. IEEE Access, 10:48855–48864, 2022.
  51. Pseudoseg: Designing pseudo labels for semantic segmentation. arXiv:2010.09713, 2020.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Lingyan Ran (8 papers)
  2. Yali Li (40 papers)
  3. Guoqiang Liang (22 papers)
  4. Yanning Zhang (170 papers)