Abstract
This study presents an unsupervised learning instance segmentation methodology using self-supervised learning Vision Transformer (ViT) and K-means methodology. The proposed instance segmentation is attracting attention as a core field of computer vision that assigns all pixels of an image to an appropriate class and localizes objects to bounding boxes. However, the task of producing high-accuracy pixel-level labels is more important than image classification and object detection. It requires high costs and a lot of time. Therefore, this study provides a clear and easy-to-understand explanation for the personalized decision-making process by using an iterative object mask refinement technique that performs class agnostic unsupervised instance segmentation using K-means clustering and self-adaptive supervised learned ViT. do. The proposed method generates pseudo labels that can be used to learn commercial instance segmentation models. The generated pseudo labels have higher accuracy than other methodologies, and the instance segmentation model learned with pseudo labels improves the existing highest performance by more than 50–80%. Therefore, in this study, without changing the structure of the learning function or model, we proposed a personalized ViT recommendation algorithm through single object discovery, multi-object discovery, and supervised learning segmentation using K-means, a simple clustering methodology, and self-supervised learning ViT.
Similar content being viewed by others
References
Liu S, Lu Qi, Qin H-F, Shi J-P, Jia J-A (2015) Path aggregation network for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8759–8768
Zhang L, Guo Y, Wang X (2022) Semantics reused context feature pyramid network for object detection in remote sensing images. J Appl Remote Sens 16(3):036509–036509
Agarwal A., Lohia P, Nagar, S, Dey K, Saha D (2018) Automated test generation to detect individual discrimination in AI models ArXiv:1809.03260 [Cs]
Adadi A, Berrada M (2018) Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6:23
Chen Y-C, Chang C-Y, Hsiao P-Y, Fu L-C (2019) Real-time multi-class instance segmentation with one-time deep embedding clustering, In: Palaiahnakote Pattern Recognition. ACPR 2019. Lecture Notes in Computer Science, 12046:223–235
Khan Z-F (2019) Automated segmentation of lung parenchyma using colour based fuzzy C-means clustering. J Electr Eng Technol 14:2163–2169
Zhang X, Li C-Z, Xue M, Wang W-B, Zhu L-H (2023) Application of deep learning in motor vibration and noise suppression based on negative magnetostrictive effect. J Electr Eng Technol 18:1931–1944
Agham N-G-H, Chaskar U-A , Samarth P-C (2021) An unsupervised learning of impedance plethysmograph for perceiving cardiac events : (Unsupervised Learning of Impedance Plethysmograph), 2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), Greater Noida, India, pp 470–475
] Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Houlsby N (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.
MS COCO validataion dataset http://cocodataset.org/#download
Hulsen T (2023) Explainable artificial intelligence (XAI): concepts and challenges in healthcare. AI 4(3):652–666
Gianfagna L, Di Cecco A (2021) Model-agnostic methods for XAI. Explainable AI with python. Springer International Publishing, Cham, pp 81–113
Sokol K, Hepburn A, Santos-Rodriguez R, Flach P (2019) bLIMEy: surrogate prediction explanations beyond LIME. arXiv preprint arXiv:1910.13016
Li Z (2022) Extracting spatial effects from machine learning model using local interpretation method: an example of SHAP and XGBoost. Comput Environ Urban Syst 96:101845
Gu W, Bai S, Kong L (2022) A review on 2D instance segmentation based on deep neural networks. Image Vis Comput 120:104401
Siméoni O, Puy G, Vo HV, Roburin S, Gidaris S, Bursuc, A, Ponce J (2021). Localizing objects with self-supervised transformers and no labels. arXiv preprint arXiv:2109.14279
Quan L, Zhang D, Yang Y, Liu Y, Qin Q (2013) Segmentation of tumor ultrasound image via region-based Ncut method. Wuhan Univ J Nat Sci 18:313–318
Akbari H-S, Yuan L-Z, Qian R, Chuang W-H, Chang S-F, Cui, Y (2021) VATT: transformers for multimodal self-supervised learning from raw video, audio and text. In: 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia
Wang Y, Shen X, Hu SX, Yuan Y, Crowley JL, Vaufreydaz D. Supplementary material self-supervised transformers for unsupervised object discovery using normalized cut
Perronnin F, Sánchez J, Liu Y (2010) Large-scale image categorization with explicit data embedding. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, pp 2297–2304
UR Rehman A, Rahim R, Nadeem S, and ul Hussain S (2019) End-to-end trained CNN encoder-decoder networks for image steganography. In Computer Vision–ECCV 2018 Workshops: Munich, Germany, Sept 8–14, 2018, Proceedings, Part IV 15. Springer International Publishing, pp 723–729
Abdusalomov AB, Islam BMS, Nasimov R, Mukhiddinov M, Whangbo TK (2023) An improved forest fire detection method based on the detectron2 model and a deep learning approach. Sensors 23(3):1512
Wettig A, Gao T, Zhong Z, Chen D (2022) Should you mask 15% in masked language modeling?. arXiv preprint arXiv:2202.08005
Wang Y, Shen X, Yuan Y, Du Y, Li M, Hu SX, Vaufreydaz D (2022) Tokencut: Segmenting objects in images and videos with self-supervised transformer and normalized cut. arXiv preprint arXiv:2209.00383
Anderson A, Dodge J, Sadarangani A, Juozapaitis Z, Newman E, Irvine J, Chattopadhyay S, Olson M, Fern A, Burnett M (2020) Mental models of mere mortals with explanations of reinforcement learning. ACM Trans Interact Intell Syst 10(2):1–37
Shin SY, Lee S, Yun ID, Kim SM, Lee KM (2018) Joint weakly and semi-supervised deep learning for localization and classification of masses in breast ultrasound images. IEEE Trans Med Imaging 38(3):762–774
Acknowledgements
This research was supported by the Daejeon University Research Grants (2022)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Cho, YB. XAI Personalized Recommendation Algorithm Using ViT and K-Means. J. Electr. Eng. Technol. (2024). https://doi.org/10.1007/s42835-024-01843-6
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42835-024-01843-6