{"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/laso-label-set-operations-networks-for-multi","title":"LaSO: Label-Set Operations networks for multi-label few-shot learning","arxiv_id":"1902.09811","date":"2019-02-26","proceeding":"CVPR 2019 6","authors":["Amit Alfassy","Leonid Karlinsky","Amit Aides","Joseph Shtok","Sivan Harary","Rogerio Feris","Raja Giryes","Alex M. Bronstein"],"abstract":"Example synthesis is one of the leading methods to tackle the problem of\nfew-shot learning, where only a small number of samples per class are\navailable. However, current synthesis approaches only address the scenario of a\nsingle category label per image. In this work, we propose a novel technique for\nsynthesizing samples with multiple labels for the (yet unhandled) multi-label\nfew-shot classification scenario. We propose to combine pairs of given examples\nin feature space, so that the resulting synthesized feature vectors will\ncorrespond to examples whose label sets are obtained through certain set\noperations on the label sets of the corresponding input pairs. Thus, our method\nis capable of producing a sample containing the intersection, union or\nset-difference of labels present in two input samples. As we show, these set\noperations generalize to labels unseen during training. This enables performing\naugmentation on examples of novel categories, thus, facilitating multi-label\nfew-shot classifier learning. We conduct numerous experiments showing promising\nresults for the label-set manipulation capabilities of the proposed approach,\nboth directly (using the classification and retrieval metrics), and in the\ncontext of performing data augmentation for multi-label few-shot learning. We\npropose a benchmark for this new and challenging task and show that our method\ncompares favorably to all the common baselines.","url_abs":"http://arxiv.org/abs/1902.09811v1","url_pdf":"http://arxiv.org/pdf/1902.09811v1.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":"laso-label-set-operations-networks-for-multi","repo_url":"https://github.com/leokarlin/LaSO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"laso-label-set-operations-networks-for-multi","repo_url":"https://github.com/nganltp/admicro-LaSO","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1902.09811","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}