{"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/deep-compressed-sensing","title":"Deep Compressed Sensing","arxiv_id":"1905.06723","date":"2019-05-16","proceeding":null,"authors":["Yan Wu","Mihaela Rosca","Timothy Lillicrap"],"abstract":"Compressed sensing (CS) provides an elegant framework for recovering sparse signals from compressed measurements. For example, CS can exploit the structure of natural images and recover an image from only a few random measurements. CS is flexible and data efficient, but its application has been restricted by the strong assumption of sparsity and costly reconstruction process. A recent approach that combines CS with neural network generators has removed the constraint of sparsity, but reconstruction remains slow. Here we propose a novel framework that significantly improves both the performance and speed of signal recovery by jointly training a generator and the optimisation process for reconstruction via meta-learning. We explore training the measurements with different objectives, and derive a family of models based on minimising measurement errors. We show that Generative Adversarial Nets (GANs) can be viewed as a special case in this family of models. Borrowing insights from the CS perspective, we develop a novel way of improving GANs using gradient information from the discriminator.","url_abs":"https://arxiv.org/abs/1905.06723v2","url_pdf":"https://arxiv.org/pdf/1905.06723v2.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":"deep-compressed-sensing","repo_url":"https://github.com/deepmind/deepmind-research/tree/master/cs_gan","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"compressed-sensing","task_name":"compressed sensing"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"cs-gan","method_name":"CS-GAN"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"euclidean-norm-regularization","method_name":"Euclidean Norm Regularization"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"gan-hinge-loss","method_name":"GAN Hinge Loss"},{"method_slug":"latent-optimisation","method_name":"Latent Optimisation"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sngan","method_name":"SNGAN"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"spectral-normalization","method_name":"Spectral Normalization"}],"datasets_introduced":[],"methods_introduced":[{"slug":"cs-gan","name":"CS-GAN","full_name":"CS-GAN"},{"slug":"euclidean-norm-regularization","name":"Euclidean Norm Regularization","full_name":"Euclidean Norm Regularization"},{"slug":"latent-optimisation","name":"Latent Optimisation","full_name":"Latent Optimisation"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.06723","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}