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

DiverseNet: Decision Diversified Semi-supervised Semantic Segmentation Networks for Remote Sensing Imagery (2311.13716v2)

Published 22 Nov 2023 in cs.CV

Abstract: Semi-supervised learning aims to help reduce the cost of the manual labelling process by leveraging valuable features extracted from a substantial pool of unlabeled data alongside a limited set of labelled data during the training phase. Since pixel-level manual labelling in large-scale remote sensing imagery is expensive, semi-supervised learning becomes an appropriate solution to this. However, most of the existing consistency learning frameworks based on network perturbation are very bulky. There is still a lack of lightweight and efficient perturbation methods to promote the diversity of features and the precision of pseudo labels during training. In order to fill this gap, we propose DiverseNet which explores multi-head and multi-model semi-supervised learning algorithms by simultaneously enhancing precision and diversity during training. The two proposed methods in the DiverseNet family, namely DiverseHead and DiverseModel, both achieve the better semantic segmentation performance in four widely utilised remote sensing imagery data sets compared to state-of-the-art semi-supervised learning methods. Meanwhile, the proposed DiverseHead architecture is simple and relatively lightweight in terms of parameter space compared to the state-of-the-art methods whilst reaching high-performance results for all the tested data sets.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 2481–2495.
  2. High-precision density mapping of marine debris and floating plastics via satellite imagery. Scientific Reports 13, 6822.
  3. Bagging predictors. Machine learning 24, 123–140.
  4. Semi-supervised learning via regularized boosting working on multiple semi-supervised assumptions. IEEE Transactions on Pattern Analysis and Machine Intelligence 33, 129–143.
  5. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE transactions on pattern analysis and machine intelligence 40, 834–848.
  6. Encoder-decoder with atrous separable convolution for semantic image segmentation, in: Proceedings of the European Conference on Computer Vision (ECCV), pp. 801–818.
  7. Semi-supervised semantic segmentation with cross pseudo supervision, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2613–2622.
  8. Improved regularization of convolutional neural networks with Cutout. arXiv preprint arXiv:1708.04552 .
  9. Land cover classification from VHR optical remote sensing images by feature ensemble deep learning network. IEEE Geoscience and Remote Sensing Letters 17, 1396–1400.
  10. n𝑛nitalic_n-CPS: Generalising cross pseudo supervision to n𝑛nitalic_n networks for semi-supervised semantic segmentation. arXiv preprint arXiv:2112.07528 .
  11. Semi-supervised semantic segmentation needs strong, varied perturbations. arXiv preprint arXiv:1906.01916 .
  12. Semantic segmentation and edge detection—approach to road detection in very high resolution satellite images. Remote Sensing 14, 613.
  13. Semi-supervised semantic segmentation via adaptive equalization learning. Advances in Neural Information Processing Systems 34, 22106–22118.
  14. Embedding regularizer learning for multi-view semi-supervised classification. IEEE Transactions on Image Processing 30, 6997–7011.
  15. Guided collaborative training for pixel-wise semi-supervised learning, in: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIII 16, Springer. pp. 429–445.
  16. MARIDA: A benchmark for Marine Debris detection from Sentinel-2 remote sensing data. PloS One 17, e0262247.
  17. Distribution aligning refinery of pseudo-label for imbalanced semi-supervised learning. Advances in neural information processing systems 33, 14567–14579.
  18. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks, in: Workshop on challenges in representation learning, ICML, Atlanta. p. 896.
  19. RoadNet: Learning to comprehensively analyze road networks in complex urban scenes from high-resolution remotely sensed images. IEEE Transactions on Geoscience and Remote Sensing 57, 2043–2056.
  20. Fully convolutional networks for semantic segmentation, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431–3440.
  21. Semi-supervised medical image segmentation via cross teaching between cnn and transformer, in: International Conference on Medical Imaging with Deep Learning, PMLR. pp. 820–833.
  22. Smooth neighbors on teacher graphs for semi-supervised learning, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 8896–8905.
  23. Confidence guided semi-supervised learning in land cover classification, in: IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, pp. 5487–5490. doi:10.1109/IGARSS52108.2023.10281770.
  24. GW4 Isambard. https://gw4.ac.uk/isambard/. Accessed: 2023-10-1.
  25. Machine Learning for Aerial Image Labeling. Ph.D. thesis. University of Toronto.
  26. Semi-supervised semantic segmentation with cross-consistency training, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12674–12684.
  27. Ensemble classification and regression-recent developments, applications and future directions. IEEE Computational intelligence magazine 11, 41–53.
  28. Global land-cover mapping with weak supervision: Outcome of the 2020 IEEE GRSS data fusion contest. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14, 3185–3199.
  29. U-Net: Convolutional networks for biomedical image segmentation, in: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, Springer. pp. 234–241.
  30. The ISPRS benchmark on urban object classification and 3D building reconstruction. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences; I-3 1, 293–298.
  31. SEN12MS–a curated dataset of georeferenced multi-spectral sentinel-1/2 imagery for deep learning and data fusion. arXiv preprint arXiv:1906.07789 .
  32. Grad-CAM: Visual explanations from deep networks via gradient-based localization. International Journal of Computer Vision 128, 336–359.
  33. Ensemble learning. RN 11, 1–34.
  34. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in Neural Information Processing Systems 30.
  35. Deep learning for land use and land cover classification based on hyperspectral and multispectral earth observation data: A review. Remote Sensing 12, 2495.
  36. Semi-supervised pixel-level scene text segmentation by mutually guided network. IEEE Transactions on Image Processing 30, 8212–8221.
  37. Semi-supervised semantic segmentation of remote sensing images with iterative contrastive network. IEEE Geoscience and Remote Sensing Letters 19, 1–5.
  38. Semi-supervised dual relation learning for multi-label classification. IEEE Transactions on Image Processing 30, 9125–9135.
  39. Lithological mapping of geological remote sensing via adversarial semi-supervised segmentation network. International Journal of Applied Earth Observation and Geoinformation 125, 103536.
  40. Semi-supervised semantic segmentation using unreliable pseudo-labels, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4248–4257.
  41. Cloud/shadow segmentation based on global attention feature fusion residual network for remote sensing imagery. International Journal of Remote Sensing 42, 2022–2045.
  42. Label propagation and contrastive regularization for semi-supervised semantic segmentation of remote sensing images. IEEE Transactions on Geoscience and Remote Sensing .
  43. CutMix: Regularization strategy to train strong classifiers with localizable features, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6023–6032.
  44. FlexMatch: Boosting semi-supervised learning with curriculum pseudo labeling. Advances in Neural Information Processing Systems 34, 18408–18419.
  45. Multi-scale dense networks for hyperspectral remote sensing image classification. IEEE Transactions on Geoscience and Remote Sensing 57, 9201–9222.
  46. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 .
  47. Pyramid scene parsing network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881–2890.
  48. HFA-Net: high frequency attention siamese network for building change detection in VHR remote sensing images. Pattern Recognition 129, 108717.
  49. Improving semantic segmentation via efficient self-training. IEEE Transactions on Pattern Analysis and Machine Intelligence .

Summary

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

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