# Surpassing Human-Level Face Verification Performance on LFW with GaussianFace

arXiv: https://arxiv.org/abs/1404.3840 · HTML: https://mlsanity.com/paper/1404.3840/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2014.

## Built on by (most cited first, 24 of 24)

- [Biometrics: Trust, but Verify](https://mlsanity.com/paper/2105.06625/) (2021)
- [SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition](https://mlsanity.com/paper/2205.12010/) (2022)
- [Efficient Explainable Face Verification based on Similarity Score Argument Backpropagation](https://mlsanity.com/paper/2304.13409/) (2023)
- [ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation](https://mlsanity.com/paper/2103.00119/) (2021)
- [Masked Face Recognition: Human vs. Machine](https://mlsanity.com/paper/2103.01924/) (2021)
- [Comparing Human and Machine Bias in Face Recognition](https://mlsanity.com/paper/2110.08396/) (2021)
- [Using Active Speaker Faces for Diarization in TV shows](https://mlsanity.com/paper/2203.15961/) (2022)
- [Facial Landmark Points Detection Using Knowledge Distillation-Based Neural Networks](https://mlsanity.com/paper/2111.07047/) (2021)
- [Recent Advances in Deep Learning Techniques for Face Recognition](https://mlsanity.com/paper/2103.10492/) (2021)
- [A Study on the Impact of Face Image Quality on Face Recognition in the Wild](https://mlsanity.com/paper/2307.02679/) (2023)
- [Beyond Spatial Explanations: Explainable Face Recognition in the Frequency Domain](https://mlsanity.com/paper/2407.11941/) (2024)
- [E-LMC: Extended Linear Model of Coregionalization for Spatial Field Prediction](https://mlsanity.com/paper/2203.00525/) (2022)
- [Learning domain-specific causal discovery from time series](https://mlsanity.com/paper/2209.05598/) (2022)
- [Harnessing Collective Intelligence Under a Lack of Cultural Consensus](https://mlsanity.com/paper/2309.09787/) (2023)
- [Sample Correlation for Fingerprinting Deep Face Recognition](https://mlsanity.com/paper/2412.20768/) (2024)
- [Single-Pixel Vision-Language Model for Intrinsic Privacy-Preserving Behavioral Intelligence](https://mlsanity.com/paper/2601.17050/) (2026)
- [On Biased Behavior of GANs for Face Verification](https://mlsanity.com/paper/2208.13061/) (2022)
- [Imperceptible Physical Attack against Face Recognition Systems via LED Illumination Modulation](https://mlsanity.com/paper/2307.13294/) (2023)
- [From the Pursuit of Universal AGI Architecture to Systematic Approach to Heterogenous AGI: Addressing Alignment, Energy, & AGI Grand Challenges](https://mlsanity.com/paper/2310.15274/) (2023)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [Network-Agnostic Knowledge Transfer for Medical Image Segmentation](https://mlsanity.com/paper/2101.09560/) (2021)
- [Making AI 'Smart': Bridging AI and Cognitive Science](https://mlsanity.com/paper/2112.15360/) (2021)
- [Generalized Attacks on Face Verification Systems](https://mlsanity.com/paper/2309.05879/) (2023)
- [Perceived face similarity reflects inverse-generative and naturalistic discriminative objectives](https://mlsanity.com/paper/2605.12619/) (2026)

## Abstract (arXiv)

Face verification remains a challenging problem in very complex conditions with large variations such as pose, illumination, expression, and occlusions. This problem is exacerbated when we rely unrealistically on a single training data source, which is often insufficient to cover the intrinsically complex face variations. This paper proposes a principled multi-task learning approach based on Discriminative Gaussian Process Latent Variable Model, named GaussianFace, to enrich the diversity of training data. In comparison to existing methods, our model exploits additional data from multiple source-domains to improve the generalization performance of face verification in an unknown target-domain. Importantly, our model can adapt automatically to complex data distributions, and therefore can well capture complex face variations inherent in multiple sources. Extensive experiments demonstrate the effectiveness of the proposed model in learning from diverse data sources and generalize to unseen domain. Specifically, the accuracy of our algorithm achieves an impressive accuracy rate of 98.52% on the well-known and challenging Labeled Faces in the Wild (LFW) benchmark. For the first time, the human-level performance in face verification (97.53%) on LFW is surpassed.