Download pdf
Study Report on Coresets Selection for Open-Set with Fine-Grained Task and Self-Supervised Machine Learning
- 1 Suzhou North America High School, Suzhou, China
- 2 Curtin Singapore, Singapore
* Author to whom correspondence should be addressed.
Abstract
The paper we studied introduces concepts about machine learning and algorithms for corsets selection. A group of researchers from KAIST have developed an effective coresets selection algorithm to help Open-set self-supervised learning on image classification tasks. Experiments are being established using big open sets and making it more fine-grained, models will be trained using the fine-grained sets in order to classify and annotate different objects in the picture. In our studies, we have experimented using pictures of aircraft to train the model. An algorithm to select coreset named SimCore is being developed, and the group of researchers had found that by merging the coreset selected from the open set with the target dataset, had made the training process of the model more efficient.
Keywords
Coreset, classification, Self supervised machine learning
[1]. Durga, B. K., & Rajesh, V. (2022). A ResNet deep learning based facial recognition design for future multimedia applications. Computers & Structures, 6-8. https://doi.org/10.1016/j.compstruc.2022.106095
[2]. Representation learning (no date) Papers With Code. Available at: https://paperswithcode.com/task/representation-learning (Accessed: 21 July 2024).
[3]. Papers with code - paper tables with annotated results for Coreset sampling from open-set for fine-grained self-supervised learning (no date) The latest in Machine Learning. Available at: https://paperswithcode.com/paper/coreset-sampling-from-open-set-for-fine/review/(Accessed: 21 July 2024).
[4]. Coresets.org. (n.d.). Coresets explained And how does it work? | coresets.org. https://coresets.org/
[5]. Jubran, I., Maalouf, A., & Feldman, D. (2019, October 19). Introduction to Coresets: Accurate coresets. arXiv.org. https://arxiv.org/abs/1910.08707
[6]. Suslov, E. (2024, February 29). What are resource constraints and how to manage them? PPM Express. https://ppm.express/blog/resource-constraints/#:~:text=The%20main%20types%20of%20resourcing%20constraints%20are%3A%201, resources%20required%20for%20a%20project.%20. . .%20More%20items
[7]. Ikotun, A. M., Ezugwu, A. E., Abualigah, L., Abuhaija, B., & Heming, J. (2023). K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data. Information Sciences, 622, 178–210. https://doi.org/10.1016/j.ins.2022.11.139
[8]. Papers with Code - Contrastive Learning. (n.d.). https://paperswithcode.com/task/contrastive-learning
Cite this article
Ma,W.;Ma,C. (2025). Study Report on Coresets Selection for Open-Set with Fine-Grained Task and Self-Supervised Machine Learning. Applied and Computational Engineering,131,8-17.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 2nd International Conference on Machine Learning and Automation
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).