{"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/spacing-loss-for-discovering-novel-categories","title":"Spacing Loss for Discovering Novel Categories","arxiv_id":"2204.10595","date":"2022-04-22","proceeding":null,"authors":["K J Joseph","Sujoy Paul","Gaurav Aggarwal","Soma Biswas","Piyush Rai","Kai Han","Vineeth N Balasubramanian"],"abstract":"Novel Class Discovery (NCD) is a learning paradigm, where a machine learning model is tasked to semantically group instances from unlabeled data, by utilizing labeled instances from a disjoint set of classes. In this work, we first characterize existing NCD approaches into single-stage and two-stage methods based on whether they require access to labeled and unlabeled data together while discovering new classes. Next, we devise a simple yet powerful loss function that enforces separability in the latent space using cues from multi-dimensional scaling, which we refer to as Spacing Loss. Our proposed formulation can either operate as a standalone method or can be plugged into existing methods to enhance them. We validate the efficacy of Spacing Loss with thorough experimental evaluation across multiple settings on CIFAR-10 and CIFAR-100 datasets.","url_abs":"https://arxiv.org/abs/2204.10595v1","url_pdf":"https://arxiv.org/pdf/2204.10595v1.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":"spacing-loss-for-discovering-novel-categories","repo_url":"https://github.com/josephkj/awesome-novel-class-discovery","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"novel-class-discovery","task_name":"Novel Class Discovery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.10595","atlas_url":"https://app.syntology.ai/?focus=2204.10595","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}