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 gen 11 eralization performance of the network. The proposed network achieves 27.13% absolute increase in accuracy over the DFW baseline.
| Original language | English |
|---|---|
| Title of host publication | 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) |
| Publisher | Institute of Electrical and Electronics Engineers |
| Pages | 25-31 |
| Number of pages | 7 |
| ISBN (Electronic) | 9781538661000 |
| DOIs | |
| Publication status | Published - 16 Dec 2018 |
| Externally published | Yes |
| Event | 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops - Salt Lake City, United States Duration: 18 Jun 2018 → 22 Jun 2018 Conference number: 31st |
Publication series
| Name | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
|---|---|
| Volume | 2018-June |
| ISSN (Print) | 2160-7508 |
| ISSN (Electronic) | 2160-7516 |
Conference
| Conference | 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops |
|---|---|
| Abbreviated title | CVPRW 2018 |
| Country/Territory | United States |
| City | Salt Lake City |
| Period | 18/06/18 → 22/06/18 |