{"id":18556645,"url":"https://github.com/ahmdtaha/svmax","last_synced_at":"2026-02-26T02:05:23.698Z","repository":{"id":98612488,"uuid":"338363447","full_name":"ahmdtaha/svmax","owner":"ahmdtaha","description":"SVMax : A Feature Embedding Regularizer","archived":false,"fork":false,"pushed_at":"2025-05-02T14:51:11.000Z","size":25,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-05-02T15:46:53.134Z","etag":null,"topics":["deep-learning","feature-embedding","machine-learning","metric-learning","pytorch","retrieval-systems","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","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/ahmdtaha.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2021-02-12T15:54:30.000Z","updated_at":"2025-05-02T14:51:15.000Z","dependencies_parsed_at":"2023-10-20T16:25:50.257Z","dependency_job_id":null,"html_url":"https://github.com/ahmdtaha/svmax","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/ahmdtaha%2Fsvmax","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ahmdtaha%2Fsvmax/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ahmdtaha%2Fsvmax/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ahmdtaha%2Fsvmax/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ahmdtaha","download_url":"https://codeload.github.com/ahmdtaha/svmax/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254349262,"owners_count":22056308,"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":["deep-learning","feature-embedding","machine-learning","metric-learning","pytorch","retrieval-systems","tensorflow"],"created_at":"2024-11-06T21:32:35.739Z","updated_at":"2026-02-26T02:05:18.677Z","avatar_url":"https://github.com/ahmdtaha.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SVMax: A Feature Embedding Regularizer\n\nThe official implementation of [`SVMax: A Feature Embedding Regularizer`](https://arxiv.org/abs/2103.02770). Singular Value Maximization (SVMax) learns a more uniform feature embedding. The SVMax regularizer supports both supervised and unsupervised learning. Our formulation mitigates model collapse and enables larger learning rates.\n\n![Contrastive Learning with and without SVMax](./svmax_40.gif)\n\n## Requirements\n\n* Python 3+ [Tested on 3.7]\n* Tensorflow 2.X [Tested on 2.0]\n\n## Usage example\nThe toy mnist script `mnist_embedding.py` is straight-forward to run -- no external dependencies. Set the variable `svmax_enabled` to turn SVMax On/Off.\n\n## Release History\n* 1.0.0\n    * Add a toy Tensorflow example on Feb 20, 2021\n    * Add a toy PyTorch example on Feb 21, 2021\n    * Add a toy MNIST project to the 2D unit circle on Mar 5, 2021\n\nContributor list\n----------------\n1. [Ahmed Taha](http://www.ahmed-taha.com)\n2. [Alex Hanson](https://github.com/j-alex-hanson)\n\n\n\n### Citation\n\n```\n@article{taha2021svmax,\n  title={SVMax: A Feature Embedding Regularizer},\n  author={Taha, Ahmed and Hanson, Alex and Shrivastava, Abhinav and Davis, Larry},\n  journal={arXiv preprint arXiv:2103.02770},\n  year={2021}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fahmdtaha%2Fsvmax","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fahmdtaha%2Fsvmax","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fahmdtaha%2Fsvmax/lists"}