Application of semi-supervised Mean Teacher to rock image segmentation

Jiashan Li; Yuxue Wang

doi:10.5566/ias.3279

Authors

Jiashan Li Northeast Petroleum University
Yuxue Wang Northeast Petroleum University

DOI:

https://doi.org/10.5566/ias.3279

Keywords:

Image segmentation, ResNet, Rock image, Self-attention, Semi-supervised learning, Unet

Abstract

Accurate segmentation of rock images is crucial for studying the internal structure and properties of rocks. To address the issue of requiring a large number of labeled images for model training in traditional image segmentation methods, this paper proposes an improved semi-supervised Mean Teacher algorithm based on ResNet34-UNet. This method achieves relatively accurate rock image segmentation using only a small amount of labeled data. Initially, we use ResNet34-UNet as the base model to create Student Model and Teacher Model with identical structures. Then, we introduce self-attention mechanism into the semi-supervised Mean Teacher algorithm to further enhance its performance in rock image segmentation. Finally, by comparing the performance of supervised and semi-supervised Mean Teacher algorithms on image segmentation tasks, we validate the effectiveness of semi-supervised learning in rock image segmentation.

References

Badrinarayanan V, Kendall A, Cipolla R (2017). Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence 39(12): 2481-95.

Cao D,Ji S,Cui R,Liu Q (2022). Multi-task learning for digital rock segmentation and characteristic parameters computation.Journal of Petroleum Science and Engineering 208: 109202.

Chen J, Zhao Z, Zhang J (2024). Predicting peak shear strength of rock fractures using tree-based models and convolutional neural network.Computers and Geotechnics 166: 105965.

Cai F, Wen J, He F, Xu W (2024). SC-Unext: A Lightweight Image Segmentation Model with Cellular Mechanism for Breast Ultrasound Tumor Diagnosis. Journal of Imaging Informatics in Medicine 37: 1505-15.

Dong K and Jiang D (2013). Ore image segmentation algorithm based on improved watershed transform. Computer Engineering and Design 34(3): 899-903.

Fan L, Yuan J, Niu X, Zha K, Ma W (2023). RockSeg: A Novel Semantic Segmentation Network Based on a Hybrid Framework Combining a Convolutional Neural Network and Transformer for Deep Space Rock Images. Remote Sensing 15(16): 3935

Han K, Sheng V, Song Y, Liu Y, Qiu C, Ma S, Liu Z (2024). Deep semi-supervised learning for medical image segmentation: A review. Expert Systems with Applications 245:123052.

Huang B, Huang T, Xu J, Min J, Hu C, Zhang Z (2024). RCNU-Net: Reparameterized convolutional network with convolutional block attention module for improved polyp image segmentation. Biomedical Signal Processing and Control 93:106138.

Huang S, Luo J, Ou Y, Pang Y, Nie X, Zhang G (2024). Sd-net: a semi-supervised double-cooperative network for liver segmentation from computed tomography (CT) images. Journal of Cancer Research and Clinical Oncology 150(2):79.

Lou L, Xin Y, Qian J, Dong Y (2024). A detail-oriented super-2D network for pulmonary artery segmentation. Biomedical Signal Processing and Control 93: 106183.

Liu Y, Wang X, Zhang Z, Deng F (2023). Deep learning in image segmentation for mineral production: A review. Computers & Geosciences 180: 105455.

Liang H and Zou J (2020). Rock image segmentation of improved semi-supervised SVMĺCFCM algorithm based on chaos. Circuits, Systems, and Signal Processing 39(2): 571- 85.

Liu Y, Shen Y, Song H, Yan F, Su Y (2024). Solar radio spectrogram segmentation algorithm based on improved Fuzzy C-Means clustering and adaptive cross filtering. Physica Scripta 99(4): 5005.

Murray G, Bourlai T, Spolaor M (2021). Mask R-CNN: Detection performance on SPEED spacecraft with image degradation. In 2021 IEEE International Conference on Big Data (Big Data) ,Orlando, FL, USA.IEEE.

Manzoor S, Qasim T, Bhatti N, Zia M (2023). Segmentation of digital rock images using texture analysis and deep network. Arabian Journal of Geosciences 16(7): 436.

Mazher M, Razzak I, Qayyum A, Tanveer M, Beier S, Khan T, et al. (2024). Self-supervised spatialtemporal transformer fusion based federated framework for 4D cardiovascular image segmentation. Information Fusion 106: 102256.

Niu Y, Mostaghimi P, Shabaninejad M, Swietojanski P, Armstrong R (2020). Digital rock segmentation for petrophysical analysis with reduced user bias using convolutional neural networks. Water Resources Research 56(2): e2019WR026597.

Roslin A, Lebedev M, Mitchell TR, Onederra IA, Leonardi CR (2023). Processing of micro-C Timages of granodiorite rock samples using convolutional neural networks (CNN). Part III: Enhancement of Scanco micro-CT images of granodiorite rocks using a 3D convolutional neural network superresolution algorithm. Minerals Engineering 195: 108028.

Ronneberger O, Fischer P, Brox T (2015). U-net: Convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention-MICCAI 2015,Cham.Springer International Publishing.

Sinha A, Aljrees T, Pandey SK, Kumar A, Banerjee P, Kumar B, et al. (2023). Semi-Supervised Clustering-Based DANA Algorithm for Data Gathering and Disease Detection in Healthcare Wireless Sensor Networks (WSN). Sensors 24(1): 18.

Tarvainen A and Valpola H (2017). Weight-averaged consistency targets improve semi-supervised deep learning results.ArXiv abs: 1703.01780.

Vaswani A, Shazeer NM, Parmar N, Uszkoreit J, Jones L, Gomez AN,et al. (2017). Attention is All you Need.ArXiv abs: 1706.03762.

Weng Y, Zhang Y, Wang W, Dening T (2024). Semi-supervised information fusion for medical image analysis: Recent progress and future perspectives. Information Fusion 106: 102263.

Liu Y and Lv J (2023). Semi-supervised Rock Image Segmentation and Recognition Based on Superpix. Advanced Engineering Science 55(2):171-183.

Zhang Z, Tian C, Gao X, Wang C, Feng X, Bai H, et al. (2022). Dynamic prototypical feature representation learning framework for semi-supervised skin lesion segmentation. Neurocomputing 507: 369-82.

Zhao F, Tang Z, Xiao Z, Liu H, Fan J, Li L (2024). Ensemble CART surrogate-assisted automatic multi-objective rough fuzzy clustering algorithm for unsupervised image segmentation. Engineering Applications of Artificial Intelligence 133: 108104.

Zhang X, Wang Z, Liu D, Sun Q, Wang J (2023). Rock thin section image classification based on depth residuals shrinkage network and attention mechanism. Earth Science Informatics 16(2): 1449-57.