# Harnessing Geometric Constraints from Emotion Labels to improve Face Verification

arXiv: https://arxiv.org/abs/2103.03862 · HTML: https://mlsanity.com/paper/2103.03862/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 57 references that are in the map.
- First posted on arXiv 5 Mar 2021.

## Builds on (most cited first, 28 of 28)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild](https://mlsanity.com/paper/1708.03985/) (2017)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [The MegaFace Benchmark: 1 Million Faces for Recognition at Scale](https://mlsanity.com/paper/1512.00596/) (2015)
- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://mlsanity.com/paper/1905.00641/) (2019)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [Massively Multitask Networks for Drug Discovery](https://mlsanity.com/paper/1502.02072/) (2015)
- [Self-supervised learning of a facial attribute embedding from video](https://mlsanity.com/paper/1808.06882/) (2018)
- [LaSO: Label-Set Operations networks for multi-label few-shot learning](https://mlsanity.com/paper/1902.09811/) (2019)
- [Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition](https://mlsanity.com/paper/1704.01631/) (2017)
- [Pose-Robust Face Recognition via Deep Residual Equivariant Mapping](https://mlsanity.com/paper/1803.00839/) (2018)
- [Deep Learning for Face Recognition: Pride or Prejudiced?](https://mlsanity.com/paper/1904.01219/) (2019)
- [Self-Supervised Learning of Face Representations for Video Face Clustering](https://mlsanity.com/paper/1903.01000/) (2019)
- [Improving One-Shot Learning through Fusing Side Information](https://mlsanity.com/paper/1710.08347/) (2017)
- [Structured Embedding Models for Grouped Data](https://mlsanity.com/paper/1709.10367/) (2017)
- [Compositional Embeddings for Multi-Label One-Shot Learning](https://mlsanity.com/paper/2002.04193/) (2020)

## Abstract (arXiv)

For the task of face verification, we explore the utility of harnessing auxiliary facial emotion labels to impose explicit geometric constraints on the embedding space when training deep embedding models. We introduce several novel loss functions that, in conjunction with a standard Triplet Loss [43], or ArcFace loss [10], provide geometric constraints on the embedding space; the labels for our loss functions can be provided using either manually annotated or automatically detected auxiliary emotion labels. Our method is implemented purely in terms of the loss function and does not require any changes to the neural network backbone of the embedding function.