{"id":15895963,"url":"https://github.com/sayakpaul/consistency-training-with-supervision","last_synced_at":"2025-09-20T20:32:20.880Z","repository":{"id":106648199,"uuid":"353252372","full_name":"sayakpaul/Consistency-Training-with-Supervision","owner":"sayakpaul","description":"Contains experimentation notebooks for my Keras Example \"Consistency Training with Supervision\".","archived":false,"fork":false,"pushed_at":"2021-04-26T01:04:27.000Z","size":1484,"stargazers_count":5,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-12-28T03:39:24.688Z","etag":null,"topics":["computer-vision","consistency-regularization","keras","robustness-experiments","tensorflow"],"latest_commit_sha":null,"homepage":"https://keras.io/examples/vision/consistency_training/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sayakpaul.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2021-03-31T06:36:37.000Z","updated_at":"2024-10-13T06:47:15.000Z","dependencies_parsed_at":null,"dependency_job_id":"24f447e3-a170-409d-91af-1c8af07b7e76","html_url":"https://github.com/sayakpaul/Consistency-Training-with-Supervision","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayakpaul%2FConsistency-Training-with-Supervision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayakpaul%2FConsistency-Training-with-Supervision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayakpaul%2FConsistency-Training-with-Supervision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayakpaul%2FConsistency-Training-with-Supervision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sayakpaul","download_url":"https://codeload.github.com/sayakpaul/Consistency-Training-with-Supervision/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":233578431,"owners_count":18697185,"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":["computer-vision","consistency-regularization","keras","robustness-experiments","tensorflow"],"created_at":"2024-10-06T09:05:04.726Z","updated_at":"2025-09-20T20:32:15.515Z","avatar_url":"https://github.com/sayakpaul.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Consistency-Training-with-Supervision\nContains experimentation notebooks for my Keras Example [Consistency Training with Supervision](https://keras.io/examples/vision/consistency_training/). This example also provides a template for performing semi-supervised / weakly supervised learning. \n\nPromising results on [CIFAR-10-C](https://github.com/hendrycks/robustness) with the process shown in the example:\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=https://i.ibb.co/HBJkM9R/image.png\u003e\u003c/img\u003e\n\u003c/p\u003e\n\n**More things one can incorporate**:\n\n* Incorporate more data during training the student. \n* Filter high confidence predictions from teacher during training the student. \n* Use recipes like [Stochastic Depth](https://arxiv.org/abs/1603.09382) for training the teacher. The current example uses [Stochastic Weight Averaging](https://arxiv.org/abs/1803.05407) to induce geometric ensembling. \n\nFull-scale experiments are available [here](https://git.io/JO55v).\n\n## Acknowledgements\n\n* [ML-GDE program](https://developers.google.com/programs/experts/) for providing GCP credits. \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsayakpaul%2Fconsistency-training-with-supervision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsayakpaul%2Fconsistency-training-with-supervision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsayakpaul%2Fconsistency-training-with-supervision/lists"}