Search

MCL_NET: Multi-Scale Collaborative Learning Network for Pellet Facies Microstructure Image Segmentation

Author(s)

Chun Zhang1,2, Yanbing Liang2,*

Affiliation(s)

1Hebei Key Laboratory of Data Science and Application, North China University of Science and Technology, Tangshan, Hebei, China 2College of Science, North China University of Science and Technology, Tangshan, Hebei, China *Corresponding Author

Abstract

The segmentation model based on traditional convolution focuses more on local features during training, while Transformers excel in long-range modeling tasks but lack direct advantages in short-range feature analysis. To achieve fine-grained segmentation of pellet microstructure images more effectively, we propose a Multi-Scale Collaborative Learning Network for Pellet facies microstructure image Segmentation (MCL_NET). The model integrates information from different scales to achieve pixel recovery and precise boundary segmentation of pellet microstructure images. In the segmentation task of pellet ore microstructure images, MCL-NET demonstrates superior experimental results, allowing for a more accurate representation of the shapes and boundaries of the pellet microstructures.

Keywords

Microstructure Image Segmentation; Encoding and Decoding Structure; Attention Mechanism; Feature Cross Complementary; Pyramid Structure

References

[1] LONG J, SHELHAMER E, DARRELL T. Fully convolu-tional networks for semantic segmenta-tion [C]//Proceedings of the IEEE conference on com-puter vision and pattern recognition. 2015:3431-3440. [2] RONNEBERGER O, FISCHER P, BROX T. U-net: Convo-lutional networks for biomedical image segmenta-tion [C]//Medical image computing and comput-er-assisted intervention–MICCAI 2015:18th interna-tional conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer International Pub-lishing, 2015:234-241. [3] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs [J]. IEEE transactions on pattern analysis and machine in-telligence, 2017, 40(4):834-848. [4] CHEN L C, PAPANDREOU G, SCHROFF F, et al. Re-thinking atrous convolution for semantic image seg-mentation [J]. arXiv preprint arXiv:1706.05587, 2017. [5] CHEN L C, ZHU Y, PAPANDREOU G, et al. Encod-er-decoder with atrous separable convolution for se-mantic image segmentation [C]//Proceedings of the Eu-ropean conference on computer vision (ECCV). 2018:801-818. [6] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [J]. Advances in neural information pro-cessing systems, 2017, 30. [7] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: Transformers for image recognition at scale [J]. arXiv preprint arXiv:2010.11929, 2020. [8] LIU Z, LIN Y, CAO Y, et al. Swin transformer: Hierarchical vision transformer using shifted win-dows [C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021:10012-10022. [9] CASTELLANOS R M, IGLESIAS J C Á, GOMES O F M, et al. Characterization of iron ore pellets by multimodal microscopy and image analysis [J]. REM-International Engineering Journal, 2018, 71:209-215. [10] CHEN J, LU Y, YU Q, et al. Transunet: Transformers make strong encoders for medical image segmentation [J]. arXiv preprint arXiv:2102.04306, 2021. [11] SANDLER M, HOWARD A, ZHU M, et al. Mobilenetv2: Inverted residuals and linear bottle-necks [C]//Proceedings of the IEEE conference on com-puter vision and pattern recognition. 2018:4510-4520. [12] CAO H, WANG Y, CHEN J, et al. Swin-unet: Unet-like pure transformer for medical image segmenta-tion [C]//European conference on computer vision. Cham: Springer Nature Switzerland, 2022:205-218. [13] HUANG X, DENG Z, LI D, et al. Missformer: An effective medical image segmentation transformer [J]. arXiv pre-print arXiv:2109.07162, 2021.