Locally Normalized Soft Contrastive Clustering for Compact Clusters
- Title
- Locally Normalized Soft Contrastive Clustering for Compact Clusters
- Authors
- Ma, Xin; KIM, WON HWA
- Date Issued
- 2022-07-26
- Publisher
- International Joint Conferences on Artificial Intelligence
- Abstract
- Recent deep clustering algorithms take advantage of self-supervised learning and self-training techniques to map the original data into a latent space, where the data embedding and clustering assignment can be jointly optimized. However, as many recent datasets are enormous and noisy, getting a clear boundary between different clusters is challenging with existing methods that mainly focus on contracting similar samples together and overlooking samples near boundary of clusters in the latent space. In this regard, we propose an end-to-end deep clustering algorithm, i.e., Locally Normalized Soft Contrastive Clustering (LNSCC). It takes advantage of similarities among each sample's local neighborhood and globally disconnected samples to leverage positiveness and negativeness of sample pairs in a contrastive way to separate different clusters. Experimental results on various datasets illustrate that our proposed approach achieves outstanding clustering performance over most of the state-of-the-art clustering methods for both image and non-image data even without convolution.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/114391
- Article Type
- Conference
- Citation
- International Joint Conference on Artificial Intelligence, IJCAI 2022, page. 3313 - 3320, 2022-07-26
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.