CS-KD: Confused Sample Knowledge Distillation for Semantic Segmentation of Aerial Imagery
Authors: Yue Sun, Lingfeng Huang, 
Qi Zhu, Dong LiangAuthors Info & Claims
Pages 266 - 278
Abstract
Currently, semantic segmentation methods based on knowledge distillation (KD) mainly focus on transferring various structured knowledge to the student network and designing corresponding optimization goals to encourage the student network to imitate the output of the teacher network. However, these methods do not consider the impact of sample quality on model training. Especially for aerial images of complex scenes, problems such as object occlusion and boundary blur caused by factors such as illumination and imaging angle will introduce many confused samples. These confused samples can lead to labeling bias or incorrect predictions. Therefore, we propose a confused sample knowledge distillation method (CS-KD) and design an adaptive sample screening strategy. During the training process, CS-KD makes full use of the prediction capabilities of the teacher and student networks at all stages to screen confused samples pixel by pixel and adjust the importance of different training samples. Experiment results verify that, based on the Potsdam and Vaihingen benchmarks, CS-KD can achieve competitive performance compared with other state-of-the art KD methods. Additionally, our research showcases that CS-KD can integrate with existing KD methods to improve their upper performance bound.
References
[1]
Pham HN et al. A new deep learning approach based on bilateral semantic segmentation models for sustainable estuarine wetland ecosystem management Sci. Total Environ. 2022 838
[2]
Trenčanová B, Proença V, and Bernardino A Development of semantic maps of vegetation cover from UAV images to support planning and management in finegrained fire-prone landscapes Remote Sens. 2022 14 5 1262
[3]
Sheng, H., Chen, X., Su, J., Rajagopal, R., Ng, A.: Effective data fusion with generalized vegetation index: evidence from land cover segmentation in agriculture. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 60–61 (2020)
[4]
Ji, C., Zhou, W., Lei, J., Ye, L.: Infrared and visible image fusion via multiscale receptive field amplification fusion network. IEEE Signal Process. Lett. (2023)
[5]
Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation (2017). arXiv:1706.05587
[6]
Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: ECCV (2018)
[7]
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2017)
[8]
Wang J et al. Deep high-resolution representation learning for visual recognition TPAMI 2020 43 10 3349-3364
[9]
Wu, J., Leng, C., Wang, Y., Hu, Q., Cheng, J.: Quantized convolutional neural networks for mobile devices. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4820–4828 (2016)
[10]
He, W., Wu, M., Liang, M., Lam, S.K.: CAP: context-aware pruning for semantic segmentation. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 960–969 (2021)
[11]
Yang, C., Zhou, H., An, Z., Jiang, X., Xu, Y., Zhang, Q.: Cross-image relational knowledge distillation for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022)
[12]
Liu, Y., Chen, K., Liu, C., Qin, Z., Luo, Z., Wang, J.: Structured knowledge distillation for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019)
[13]
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
[14]
Badrinarayanan V, Kendall A, and Cipolla R SegNet: a deep convolutional encoder-decoder architecture for image segmentation IEEE Trans. Pattern Anal. Mach. Intell. 2017 39 12 2481-2495
[15]
Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: ENet: a deep neural network architecture for real-time semantic segmentation (2016). arXiv:1606.02147
[16]
Zhao, H., Qi, X., Shen, X., Shi, J., Jia, J.: ICNet for real-time semantic segmentation on high-resolution images. In: ECCV (2018)
[17]
Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: BiSeNet: Bilateral segmentation network for real-time semantic segmentation. In: ECCV (2018)
[18]
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NeurIPS (2015)
[19]
Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. In: ICLR (2017)
[20]
Peng, B., et al.: Correlation congruence for knowledge distillation. In: ICCV (2019)
[21]
Wang, Y., Zhou, W., Jiang, T., Bai, X., Xu, Y.: Intra-class feature variation distillation for semantic segmentation. In: ECCV (2020)
[22]
Shu, C., Liu, Y., Gao, J., Yan, Z., Shen, C.: Channel-wise knowledge distillation for dense prediction. In: ICCV (2021)
[23]
Feng Y, Sun X, Diao W, Li J, and Gao X Double similarity distillation for semantic image segmentation TIP 2021 30 5363-5376
[24]
Yu T, Kumar S, Gupta A, Levine S, Hausman K, and Finn C Gradient surgery for multi-task learning Adv. Neural. Inf. Process. Syst. 2020 33 5824-5836
[25]
Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? NeurIPS 30 (2017)
[26]
Rottensteiner, F., Sohn, G., Gerke, M., Wegner, J.D.: ISPRS Semantic Labeling Contest. ISPRS, Leopoldshöhe, Germany 1(4), 4 (2014)
[27]
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2016)
[28]
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
[29]
Russakovsky O et al. ImageNet large scale visual recognition challenge Int. J. Comput. Vis. 2015 115 211-252
Index Terms
- CS-KD: Confused Sample Knowledge Distillation for Semantic Segmentation of Aerial Imagery
Index terms have been assigned to the content through auto-classification.
Recommendations
Optimal representative sample weighting
AbstractWe consider the problem of assigning weights to a set of samples or data records, with the goal of achieving a representative weighting, which happens when certain sample averages of the data are close to prescribed values. We frame the problem of ...
Semi- and Weakly- Supervised Semantic Segmentation with Deep Convolutional Neural Networks
MM '15: Proceedings of the 23rd ACM international conference on MultimediaSuccessful semantic segmentation methods typically rely on the training datasets containing a large number of pixel-wise labeled images. To alleviate the dependence on such a fully annotated training dataset, in this paper, we propose a semi- and weakly-...
Marginal samples for knowledge distillation
AbstractPrevious work like Category Structure Knowledge Distillation proposes to construct category-wise relations for knowledge distillation by introducing intra-category and inter-category relations based on category centers. However, ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Aug 2024
492 pages
ISBN:978-981-97-5599-8
DOI:10.1007/978-981-97-5600-1
- Editors:
- De-Shuang Huang,
- Chuanlei Zhang,
- Qinhu Zhang
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 05 August 2024
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 16 Nov 2024
Other Metrics
Citations
View Options
View options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in