{"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/inferencing-based-on-unsupervised-learning-of","title":"Inferencing Based on Unsupervised Learning of Disentangled Representations","arxiv_id":"1803.02627","date":"2018-03-07","proceeding":null,"authors":["Tobias Hinz","Stefan Wermter"],"abstract":"Combining Generative Adversarial Networks (GANs) with encoders that learn to\nencode data points has shown promising results in learning data representations\nin an unsupervised way. We propose a framework that combines an encoder and a\ngenerator to learn disentangled representations which encode meaningful\ninformation about the data distribution without the need for any labels. While\ncurrent approaches focus mostly on the generative aspects of GANs, our\nframework can be used to perform inference on both real and generated data\npoints. Experiments on several data sets show that the encoder learns\ninterpretable, disentangled representations which encode descriptive properties\nand can be used to sample images that exhibit specific characteristics.","url_abs":"http://arxiv.org/abs/1803.02627v1","url_pdf":"http://arxiv.org/pdf/1803.02627v1.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":"inferencing-based-on-unsupervised-learning-of","repo_url":"https://github.com/tohinz/Bidirectional-InfoGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"inferencing-based-on-unsupervised-learning-of","repo_url":"https://github.com/kevinm54/keras-bidirectional-infogan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"unsupervised-image-classification","task_name":"Unsupervised Image Classification"},{"task_slug":"unsupervised-mnist","task_name":"Unsupervised MNIST"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-image-classification-on-mnist","task":"Unsupervised Image Classification","dataset":"MNIST","model":"Bidirectional InfoGAN","rank_in_archive_order":6,"of":10,"metrics":{"Accuracy":"96.61"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}