{"id":13736577,"url":"https://github.com/ilia10000/LO-Shot","last_synced_at":"2025-05-08T12:33:17.087Z","repository":{"id":37202430,"uuid":"270073370","full_name":"ilia10000/LO-Shot","owner":"ilia10000","description":"Papers and code related to 'Less Than One'-Shot (LO-Shot) Learning","archived":false,"fork":false,"pushed_at":"2024-07-21T19:41:10.000Z","size":15341,"stargazers_count":84,"open_issues_count":5,"forks_count":13,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-08-04T03:06:51.230Z","etag":null,"topics":["classification","deep-learning","deep-neural-networks","few-shot-learning","knn-classifier","machine-learning","one-shot-learning","supervised-learning"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ilia10000.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2020-06-06T18:50:52.000Z","updated_at":"2024-07-21T19:41:13.000Z","dependencies_parsed_at":"2024-04-24T20:41:59.340Z","dependency_job_id":"35fc27fe-8390-41eb-81e4-995f01964fa0","html_url":"https://github.com/ilia10000/LO-Shot","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ilia10000%2FLO-Shot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ilia10000%2FLO-Shot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ilia10000%2FLO-Shot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ilia10000%2FLO-Shot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ilia10000","download_url":"https://codeload.github.com/ilia10000/LO-Shot/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224732129,"owners_count":17360416,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["classification","deep-learning","deep-neural-networks","few-shot-learning","knn-classifier","machine-learning","one-shot-learning","supervised-learning"],"created_at":"2024-08-03T03:01:24.393Z","updated_at":"2024-11-15T04:32:07.285Z","avatar_url":"https://github.com/ilia10000.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"# Papers related to 'Less Than One'-Shot (LO-Shot) Learning\n## Papers found in this repo\n### Paper 1 - 'Less Than One'-Shot Learning: Learn N Classes from M\u003cN Samples\nPreprint - https://arxiv.org/abs/2009.08449 \n\nPublished - In AAAI 2021 Proceedings\n\nCode and appendix - [Paper1 directory](Paper1/)\n\nTL;DR - Explore the decision landscapes generated by soft-label k-Nearest Neighbors classifiers in the 'less than one'-shot learning setting.\n\nPress coverage - LO-Shot Learning has received significant [press coverage](Paper1/press_coverage.md).\n\nOnline demo - [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/ilia10000/SLkNN/master?filepath=%2Fsoft-knn%2Fsoft_knn_vis.ipynb)\n\n### Paper 2 - Optimal 1-NN Prototypes for Pathological Geometries\nPreprint - https://arxiv.org/abs/2011.00228\n\nPublished - In PeerJ Computer Science\n\nCode - [Paper2 directory](Paper2/)\n\nTL;DR - Design optimal 1-NN prototypes even in pathological cases where most prototype methods fail.\n\n### Paper 3 - One Line to Rule Them All: Generating LO-Shot Soft-Label Prototypes\nPreprint - https://arxiv.org/abs/2102.07834\n\nPublished - In IJCNN 2021 Proceedings\n\nCode - [Paper3 directory](Paper3/)\n\nTL;DR - Represent your training dataset with fewer prototypes than even the number of classes found in the data.\n\n### Paper 4 - Can humans do less-than-one-shot learning?\nPreprint - https://arxiv.org/abs/2202.04670\n\nPublished - In CogSci 2022 Proceedings\n\nCode - [LOSLP directory](LOSLP/)\n\nTL;DR - Humans can also do LO-shot learning.\n\n### Paper 5 - Using Compositionality to Learn Many Categories from Few Examples\nPreprint - https://osf.io/preprints/psyarxiv/upn8e\n\nPublished - In CogSci 2024 Proceedings\n\nCode - TBA\n\nTL;DR - Humans are better at LO-shot learning when using techniques like compositional generalization.\n\n## Papers found in other repos\n\n### Paper - Soft-Label Dataset Distillation and Text Dataset Distillation\nPreprint - https://arxiv.org/abs/1910.02551v3\n\nCode - https://github.com/ilia10000/dataset-distillation\n\nTL;DR - Experiments with soft-label dataset distillation (an algorithm for generating small synthetic datasets that train neural networks to the same performance as when training on the original data) provided the first evidence of LO-Shot Learning in neural networks. \n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Filia10000%2FLO-Shot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Filia10000%2FLO-Shot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Filia10000%2FLO-Shot/lists"}