{"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/task-aware-compressed-sensing-with-generative","title":"Task-Aware Compressed Sensing with Generative Adversarial Networks","arxiv_id":"1802.01284","date":"2018-02-05","proceeding":null,"authors":["Maya Kabkab","Pouya Samangouei","Rama Chellappa"],"abstract":"In recent years, neural network approaches have been widely adopted for\nmachine learning tasks, with applications in computer vision. More recently,\nunsupervised generative models based on neural networks have been successfully\napplied to model data distributions via low-dimensional latent spaces. In this\npaper, we use Generative Adversarial Networks (GANs) to impose structure in\ncompressed sensing problems, replacing the usual sparsity constraint. We\npropose to train the GANs in a task-aware fashion, specifically for\nreconstruction tasks. We also show that it is possible to train our model\nwithout using any (or much) non-compressed data. Finally, we show that the\nlatent space of the GAN carries discriminative information and can further be\nregularized to generate input features for general inference tasks. We\ndemonstrate the effectiveness of our method on a variety of reconstruction and\nclassification problems.","url_abs":"http://arxiv.org/abs/1802.01284v1","url_pdf":"http://arxiv.org/pdf/1802.01284v1.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":"task-aware-compressed-sensing-with-generative","repo_url":"https://github.com/po0ya/csgan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"compressed-sensing","task_name":"compressed sensing"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.01284","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}