Virtual Adversarial Training for Semi-supervised Verification Tasks

Vahid Noroozi, Sara Bahaadini, Lei Zheng, Sihong Xie, Philip S. Yu

Abstract: The goal in verification tasks is to determine the similarity of two samples or verifies if they belong to the same category or not. In this paper, we propose a semi-supervised embedding technique for verification tasks using deep neural networks. The proposed model exploits the unlabeled data by making the model robust to the perturbation of the input with virtual adversarial training. It increases the generalization of the embedding function and prevents overfitting which are crucial in verification tasks. The proposed algorithm, named VerVAT, is evaluated on several verification tasks and compared with state-of-the-art algorithms. Experiments show the effectiveness of VerVAT especially in cases where limited labeled data is available.