In recent years, due to the emergence of deep learning, face recognition has\nachieved exceptional success. However, many of these deep face recognition\nmodels perform relatively poorly in handling profile faces compared to frontal\nfaces. The major reason for this poor performance is that it is inherently\ndifficult to learn large pose invariant deep representations that are useful\nfor profile face recognition. In this paper, we hypothesize that the profile\nface domain possesses a gradual connection with the frontal face domain in the\ndeep feature space. We look to exploit this connection by projecting the\nprofile faces and frontal faces into a common latent space and perform\nverification or retrieval in the latent domain. We leverage a coupled\ngenerative adversarial network (cpGAN) structure to find the hidden\nrelationship between the profile and frontal images in a latent common\nembedding subspace. Specifically, the cpGAN framework consists of two GAN-based\nsub-networks, one dedicated to the frontal domain and the other dedicated to\nthe profile domain. Each sub-network tends to find a projection that maximizes\nthe pair-wise correlation between two feature domains in a common embedding\nfeature subspace. The efficacy of our approach compared with the\nstate-of-the-art is demonstrated using the CFP, CMU MultiPIE, IJB-A, and IJB-C\ndatasets.\n