Feature Ensemble Networks with Re-Ranking for Recognizing Disguised Faces in the Wild
Abstract
Recognizing a person's face images with intentional/unintentional disguising effects such as make-up, plastic surgery, artificial wearables (hats, eye-glasses) is a challenging task. We propose a Feature EnsemBle Network (FEBNet) for recognizing Disguised Faces in the Wild (DFW). FEBNet encompasses multiple base networks (SE-ResNet50, Inception-ResNet-V1) pretrained on large-scale face recognition datasets (MS-Celeb-1M, VGGFace2) and fine-tuned on DFW training dataset. During the fine-tuning phase, we propose to use two novel objective functions, namely, 1) Category loss, 2) Impersonator Triplet loss along with two prevalent objective functions: Identity loss, Inter-person Triplet loss. To further improve the performance, we apply a state-of-the-art re-ranking strategy as a post-processing step. Extensive ablation studies and evaluation results show that FEBNet significantly outperforms the baseline models.
Cite
Text
Subramaniam et al. "Feature Ensemble Networks with Re-Ranking for Recognizing Disguised Faces in the Wild." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00066Markdown
[Subramaniam et al. "Feature Ensemble Networks with Re-Ranking for Recognizing Disguised Faces in the Wild." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/subramaniam2019iccvw-feature/) doi:10.1109/ICCVW.2019.00066BibTeX
@inproceedings{subramaniam2019iccvw-feature,
title = {{Feature Ensemble Networks with Re-Ranking for Recognizing Disguised Faces in the Wild}},
author = {Subramaniam, Arulkumar and Sridhar, Ajay Narayanan and Mittal, Anurag},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2019},
pages = {532-541},
doi = {10.1109/ICCVW.2019.00066},
url = {https://mlanthology.org/iccvw/2019/subramaniam2019iccvw-feature/}
}