SymFace: Additional Facial Symmetry Loss for Deep Face Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913506048081920 |
|---|---|
| author | Prakash, Pritesh Jerripothula, Koteswar Rao Sam, Ashish Jacob Singh, Prinsh Kumar Umamaheswaran, S |
| author_facet | Prakash, Pritesh Jerripothula, Koteswar Rao Sam, Ashish Jacob Singh, Prinsh Kumar Umamaheswaran, S |
| contents | Over the past decade, there has been a steady advancement in enhancing face recognition algorithms leveraging advanced machine learning methods. The role of the loss function is pivotal in addressing face verification problems and playing a game-changing role. These loss functions have mainly explored variations among intra-class or inter-class separation. This research examines the natural phenomenon of facial symmetry in the face verification problem. The symmetry between the left and right hemi faces has been widely used in many research areas in recent decades. This paper adopts this simple approach judiciously by splitting the face image vertically into two halves. With the assumption that the natural phenomena of facial symmetry can enhance face verification methodology, we hypothesize that the two output embedding vectors of split faces must project close to each other in the output embedding space. Inspired by this concept, we penalize the network based on the disparity of embedding of the symmetrical pair of split faces. Symmetrical loss has the potential to minimize minor asymmetric features due to facial expression and lightning conditions, hence significantly increasing the inter-class variance among the classes and leading to more reliable face embedding. This loss function propels any network to outperform its baseline performance across all existing network architectures and configurations, enabling us to achieve SoTA results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_11816 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SymFace: Additional Facial Symmetry Loss for Deep Face Recognition Prakash, Pritesh Jerripothula, Koteswar Rao Sam, Ashish Jacob Singh, Prinsh Kumar Umamaheswaran, S Computer Vision and Pattern Recognition 68T45 (Primary) I.4.9 Over the past decade, there has been a steady advancement in enhancing face recognition algorithms leveraging advanced machine learning methods. The role of the loss function is pivotal in addressing face verification problems and playing a game-changing role. These loss functions have mainly explored variations among intra-class or inter-class separation. This research examines the natural phenomenon of facial symmetry in the face verification problem. The symmetry between the left and right hemi faces has been widely used in many research areas in recent decades. This paper adopts this simple approach judiciously by splitting the face image vertically into two halves. With the assumption that the natural phenomena of facial symmetry can enhance face verification methodology, we hypothesize that the two output embedding vectors of split faces must project close to each other in the output embedding space. Inspired by this concept, we penalize the network based on the disparity of embedding of the symmetrical pair of split faces. Symmetrical loss has the potential to minimize minor asymmetric features due to facial expression and lightning conditions, hence significantly increasing the inter-class variance among the classes and leading to more reliable face embedding. This loss function propels any network to outperform its baseline performance across all existing network architectures and configurations, enabling us to achieve SoTA results. |
| title | SymFace: Additional Facial Symmetry Loss for Deep Face Recognition |
| topic | Computer Vision and Pattern Recognition 68T45 (Primary) I.4.9 |
| url | https://arxiv.org/abs/2409.11816 |