{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/information-maximization-clustering-via-multi","title":"Information Maximization Clustering via Multi-View Self-Labelling","arxiv_id":"2103.07368","date":"2021-03-12","proceeding":null,"authors":["Foivos Ntelemis","Yaochu Jin","Spencer A. Thomas"],"abstract":"Image clustering is a particularly challenging computer vision task, which aims to generate annotations without human supervision. Recent advances focus on the use of self-supervised learning strategies in image clustering, by first learning valuable semantics and then clustering the image representations. These multiple-phase algorithms, however, increase the computational time and their final performance is reliant on the first stage. By extending the self-supervised approach, we propose a novel single-phase clustering method that simultaneously learns meaningful representations and assigns the corresponding annotations. This is achieved by integrating a discrete representation into the self-supervised paradigm through a classifier net. Specifically, the proposed clustering objective employs mutual information, and maximizes the dependency between the integrated discrete representation and a discrete probability distribution. The discrete probability distribution is derived though the self-supervised process by comparing the learnt latent representation with a set of trainable prototypes. To enhance the learning performance of the classifier, we jointly apply the mutual information across multi-crop views. Our empirical results show that the proposed framework outperforms state-of-the-art techniques with the average accuracy of 89.1% and 49.0%, respectively, on CIFAR-10 and CIFAR-100/20 datasets. Finally, the proposed method also demonstrates attractive robustness to parameter settings, making it ready to be applicable to other datasets.","url_abs":"https://arxiv.org/abs/2103.07368v2","url_pdf":"https://arxiv.org/pdf/2103.07368v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"information-maximization-clustering-via-multi","repo_url":"https://github.com/foiv0s/imc-swav-pub","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-clustering","task_name":"Image Clustering"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-clustering-on-cifar-10","task":"Image Clustering","dataset":"CIFAR-10","model":"IMC-SwAV (Best)","rank_in_archive_order":14,"of":40,"metrics":{"ARI":"0.8","Accuracy":"0.897","Backbone":"ResNet-18","NMI":"0.818","Train set":"Train"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-cifar-10","task":"Image Clustering","dataset":"CIFAR-10","model":"IMC-SwAV (Avg+-)","rank_in_archive_order":15,"of":40,"metrics":{"ARI":"0.79","Accuracy":"0.891","Backbone":"ResNet-18","NMI":"0.811","Train set":"Train"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-cifar-100","task":"Image Clustering","dataset":"CIFAR-100","model":"IMC-SwAV (Best)","rank_in_archive_order":12,"of":30,"metrics":{"ARI":"0.361","Accuracy":"0.519","NMI":"0.527","Train Set":"Train"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-cifar-100","task":"Image Clustering","dataset":"CIFAR-100","model":"IMC-SwAV (Avg+-)","rank_in_archive_order":14,"of":30,"metrics":{"ARI":"0.337","Accuracy":"0.49","NMI":"0.503"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-stl-10","task":"Image Clustering","dataset":"STL-10","model":"IMC-SwAV (Best)","rank_in_archive_order":10,"of":29,"metrics":{"ARI":"0.716","Accuracy":"0.853","Backbone":"ResNet-18","NMI":"0.747","Train Split":"Train"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-stl-10","task":"Image Clustering","dataset":"STL-10","model":"IMC-SwAV (Avg+-)","rank_in_archive_order":13,"of":29,"metrics":{"ARI":"0.685","Accuracy":"0.831","Backbone":"ResNet-18","NMI":"0.729","Train Split":"Train"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-tiny-imagenet","task":"Image Clustering","dataset":"Tiny-ImageNet","model":"IMC-SwAV (Best)","rank_in_archive_order":4,"of":14,"metrics":{"ARI":"0.146","Accuracy":"0.282","NMI":"0.526"},"uses_additional_data":false},{"leaderboard":"/sota/image-clustering-on-tiny-imagenet","task":"Image Clustering","dataset":"Tiny-ImageNet","model":"IMC-SwAV (Avg+-)","rank_in_archive_order":5,"of":14,"metrics":{"ARI":"0.143","Accuracy":"0.279","NMI":"0.485"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}