DisguiseNet : A Contrastive Approach for Disguised Face Verification in the Wild
This addresses face verification challenges in real-world scenarios with disguises, but it is incremental as it builds on existing methods with data augmentation.
The paper tackled the problem of verifying identities from disguised faces in the wild, achieving a 27.13% absolute increase in accuracy over the baseline on the DFW dataset.
This paper describes our approach for the Disguised Faces in the Wild (DFW) 2018 challenge. The task here is to verify the identity of a person among disguised and impostors images. Given the importance of the task of face verification it is essential to compare methods across a common platform. Our approach is based on VGG-face architecture paired with Contrastive loss based on cosine distance metric. For augmenting the data set, we source more data from the internet. The experiments show the effectiveness of the approach on the DFW data. We show that adding extra data to the DFW dataset with noisy labels also helps in increasing the generalization performance of the network. The proposed network achieves 27.13% absolute increase in accuracy over the DFW baseline.