2018/02/05 by Maya Kabkab, Kabkab, Maya, Pouya Samangouei +3 · 24 citations
Computer Science · Engineering · Mathematics · #Adversarial system #Artificial intelligence #Artificial neural network #Compressed sensing #Computer science #Constraint (computer-aided design) #Deep learning #Discriminative model #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Generative adversarial network #Generative grammar #Generative model #Image and Signal Denoising Methods #Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Sparse and Compressive Sensing Techniques #Task (project management) #Variety (cybernetics) #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1802.01284
published in arXiv (Cornell University) (Cornell University) · Accepted for publication at the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)
arxiv created 2018/02/05 · openalex publication_date 2018/02/05 · arxiv updated 2018/02/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In recent years, neural network approaches have been widely adopted for machine learning tasks, with applications in computer vision. More recently, unsupervised generative models based on neural networks have been successfully applied to model data distributions via low-dimensional latent spaces. In this paper, we use Generative Adversarial Networks (GANs) to impose structure in compressed sensing problems, replacing the usual sparsity constraint. We propose to train the GANs in a task-aware fashion, specifically for reconstruction tasks. We also show that it is possible to train our model without using any (or much) non-compressed data. Finally, we show that the latent space of the GAN carries discriminative information and can further be regularized to generate input features for general inference tasks. We demonstrate the effectiveness of our method on a variety of reconstruction and classification problems.