# DisguiseNet : A Contrastive Approach for Disguised Face Verification in the Wild

Source: [DisguiseNet : A Contrastive Approach for Disguised Face Verification in the Wild](<https://www.sota2.com/research/paper/68fa644e1e209131cea03e63>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T02:54:40.511Z

Authors: Skand Vishwanath Peri, Abhinav Dhall

Published: 2018-04-25T16:32:07.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Face Verification on DFW (test)](<https://www.sota2.com/research/sota/face-verification-on-dfw-test.md>): Face Verification; DFW (test); GAR @ 0.1% FAR: 23.25.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1804.09669>)

[PDF](<https://arxiv.org/pdf/1804.09669.pdf>)

[Implementation](<https://github.com/pvskand/DisguiseNet>)