| dc.contributor.author | HU Shen, QIAN Yuhua, WANG Jieting, LI Feijiang, LYU Wei | |
| dc.contributor.other | 1 School of Computer and Information Technology,Shanxi University,Taiyuan 030006,China;2 Shanxi University Key Laboratory of Computational Intelligence and Chinese Information Processing,Ministry of Education,Taiyuan 030006,China;3 Institute of Big Data Science and Industry,Shanxi University,Taiyuan 030006,China | |
| dc.date.accessioned | 2025-08-27T02:34:34Z | |
| dc.date.accessioned | 2025-10-08T08:24:31Z | |
| dc.date.available | 2025-10-08T08:24:31Z | |
| dc.date.issued | 01-09-2023 | |
| dc.identifier.uri | http://digilib.fisipol.ugm.ac.id/repo/handle/15717717/35808 | |
| dc.description.abstract | Image clustering reduces the dimensionality of image data,extracts effective features through representation learning,and performs cluster analysis.When there are many categories of image data,the complexity of data distribution and the density of clusters seriously affect the practicability of existing methods.To this end,this paper proposes a super-multi-class deep image clustering model based on contrastive learning,which is mainly divided into three stages:firstly,improving the contrastive lear-ning method to train the feature model to make the cluster distribution uniform;secondly,based on the principle of semantic similarity,the perspective mines instance semantic nearest neighbor information;and finally,the instance and its nearest neighbors are used as self-supervised information to train a clustering model.According to the different types of experiments,ablation experiments and contrast experiments are designed in this paper.The ablation experiments prove that the proposed method could make the clusters evenly distributed in the mapping space and mine the semantic nearest neighbor information reliably.In the comparative experiments,it's compared with the advanced algorithms on 7 benchmark datasets.On the ImageNet-200 class dataset,it's accuracy is 10.6% higher than the advanced method.It's accuracy rate on the ImageNet-1000 class dataset is higher than that of the advanced algorithm,which improves by 9.2%. | |
| dc.language.iso | ZH | |
| dc.publisher | Editorial office of Computer Science | |
| dc.subject.lcc | Computer software | |
| dc.title | Super Multi-class Deep Image Clustering Model Based on Contrastive Learning | |
| dc.type | Article | |
| dc.description.keywords | super multi-class clustering|contrastive learning|feature model|semantic similarity|image clustering | |
| dc.description.pages | 192-201 | |
| dc.description.doi | 10.11896/jsjkx.220900133 | |
| dc.title.journal | Jisuanji kexue | |
| dc.identifier.oai | f50d912e85b54bef9811f710f1f4405c | |
| dc.journal.info | Volume 50, Issue 9 | |
