Under review as a conference paper at ICLR 2016 UNSUPERVISED REPRESENTATION LEARNING WITH DEEP CONVOLUTIONAL GENERATIVE ADVERSARIAL NETWORKS Alec Radford & Luke Metz indico Research Boston, MA {alec,luke}@indico.io Soumith Chintala Facebook AI Research New York, NY soumith@fb.com ABSTRACT In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsuper- vised learning. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, we show convincing evidence that our deep convolu- tional adversarial pair learns a hierarchy of represent
