{"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/self-contrastive-learning","title":"Self-Contrastive Learning: Single-viewed Supervised Contrastive Framework using Sub-network","arxiv_id":"2106.15499","date":"2021-06-29","proceeding":null,"authors":["Sangmin Bae","Sungnyun Kim","Jongwoo Ko","Gihun Lee","Seungjong Noh","Se-Young Yun"],"abstract":"Contrastive loss has significantly improved performance in supervised classification tasks by using a multi-viewed framework that leverages augmentation and label information. The augmentation enables contrast with another view of a single image but enlarges training time and memory usage. To exploit the strength of multi-views while avoiding the high computation cost, we introduce a multi-exit architecture that outputs multiple features of a single image in a single-viewed framework. To this end, we propose Self-Contrastive (SelfCon) learning, which self-contrasts within multiple outputs from the different levels of a single network. The multi-exit architecture efficiently replaces multi-augmented images and leverages various information from different layers of a network. We demonstrate that SelfCon learning improves the classification performance of the encoder network, and empirically analyze its advantages in terms of the single-view and the sub-network. Furthermore, we provide theoretical evidence of the performance increase based on the mutual information bound. For ImageNet classification on ResNet-50, SelfCon improves accuracy by +0.6% with 59% memory and 48% time of Supervised Contrastive learning, and a simple ensemble of multi-exit outputs boosts performance up to +1.5%. Our code is available at https://github.com/raymin0223/self-contrastive-learning.","url_abs":"https://arxiv.org/abs/2106.15499v6","url_pdf":"https://arxiv.org/pdf/2106.15499v6.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":"self-contrastive-learning","repo_url":"https://github.com/raymin0223/self-contrastive-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"self-contrastive-learning","repo_url":"https://github.com/delyan-boychev/grad-cache-con-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.15499","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}