TL;DR
DisguiseNet employs a contrastive learning approach with data augmentation to improve face verification accuracy on disguised faces in challenging real-world scenarios.
Contribution
The paper introduces a contrastive learning method using VGG-face architecture and data augmentation to enhance disguised face verification performance.
Findings
Achieved 27.13% accuracy increase over baseline.
Data augmentation with noisy labels improves generalization.
Effective on the Disguised Faces in the Wild dataset.
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
