{"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/mv-mr-multi-views-and-multi-representations","title":"MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation","arxiv_id":"2303.12130","date":"2023-03-21","proceeding":null,"authors":["Vitaliy Kinakh","Mariia Drozdova","Slava Voloshynovskiy"],"abstract":"We present a new method of self-supervised learning and knowledge distillation based on the multi-views and multi-representations (MV-MR). The MV-MR is based on the maximization of dependence between learnable embeddings from augmented and non-augmented views, jointly with the maximization of dependence between learnable embeddings from augmented view and multiple non-learnable representations from non-augmented view. We show that the proposed method can be used for efficient self-supervised classification and model-agnostic knowledge distillation. Unlike other self-supervised techniques, our approach does not use any contrastive learning, clustering, or stop gradients. MV-MR is a generic framework allowing the incorporation of constraints on the learnable embeddings via the usage of image multi-representations as regularizers. Along this line, knowledge distillation is considered a particular case of such a regularization. MV-MR provides the state-of-the-art performance on the STL10 and ImageNet-1K datasets among non-contrastive and clustering-free methods. We show that a lower complexity ResNet50 model pretrained using proposed knowledge distillation based on the CLIP ViT model achieves state-of-the-art performance on STL10 linear evaluation. The code is available at: https://github.com/vkinakh/mv-mr","url_abs":"https://arxiv.org/abs/2303.12130v2","url_pdf":"https://arxiv.org/pdf/2303.12130v2.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":"mv-mr-multi-views-and-multi-representations","repo_url":"https://github.com/vkinakh/mv-mr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"linear-evaluation","task_name":"Linear evaluation"},{"task_slug":"self-supervised-image-classification","task_name":"Self-Supervised Image Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"unsupervised-image-classification","task_name":"Unsupervised Image Classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/knowledge-distillation-on-cifar-100","task":"Knowledge Distillation","dataset":"CIFAR-100","model":"MV-MR (T: CLIP/ViT-B-16 S: resnet50)","rank_in_archive_order":3,"of":27,"metrics":{"Top-1 Accuracy (%)":"78.6"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-image-classification-on","task":"Self-Supervised Image Classification","dataset":"ImageNet","model":"MV-MR","rank_in_archive_order":83,"of":144,"metrics":{"Top 1 Accuracy":"74.5%","Top 5 Accuracy":"92.1"},"uses_additional_data":false},{"leaderboard":"/sota/self-supervised-learning-on-stl-10","task":"Self-Supervised Learning","dataset":"STL-10","model":"MV-MR","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy":"89.67"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-image-classification-on-cifar-20","task":"Unsupervised Image Classification","dataset":"CIFAR-20","model":"MV-MR","rank_in_archive_order":1,"of":14,"metrics":{"Accuracy":"73.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-image-classification-on-stl-10","task":"Unsupervised Image Classification","dataset":"STL-10","model":"MV-MR","rank_in_archive_order":3,"of":9,"metrics":{"Accuracy":"89.67"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}