# Unsupervised Deep Learning Image Verification Method

arXiv: https://arxiv.org/abs/2312.14395 · HTML: https://mlsanity.com/paper/2312.14395/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 43 references that are in the map.
- First posted on arXiv 22 Dec 2023.

## Builds on (most cited first, 10 of 10)

- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition](https://mlsanity.com/paper/2005.10497/) (2020)
- [An Efficient Training Approach for Very Large Scale Face Recognition](https://mlsanity.com/paper/2105.10375/) (2021)
- [Attentional Feature-Pair Relation Networks for Accurate Face Recognition](https://mlsanity.com/paper/1908.06255/) (2019)
- [SCOPE: Secure Compiling of PLCs in Cyber-Physical Systems](https://mlsanity.com/paper/2012.12529/) (2020)
- [Image Clustering using Restricted Boltzman Machine](https://mlsanity.com/paper/2312.13845/) (2023)
- [Deep Learning Based Face Recognition Method using Siamese Network](https://mlsanity.com/paper/2312.14001/) (2023)
- [Autoencoder Based Face Verification System](https://mlsanity.com/paper/2312.14301/) (2023)

## Built on by (most cited first, 1 of 1)

- [Federated Learning Method for Preserving Privacy in Face Recognition System](https://mlsanity.com/paper/2403.05344/) (2024)

## Abstract (arXiv)

Although deep learning are commonly employed for image recognition, usually huge amount of labeled training data is required, which may not always be readily available. This leads to a noticeable performance disparity when compared to state-of-the-art unsupervised face verification techniques. In this work, we propose a method to narrow this gap by leveraging an autoencoder to convert the face image vector into a novel representation. Notably, the autoencoder is trained to reconstruct neighboring face image vectors rather than the original input image vectors. These neighbor face image vectors are chosen through an unsupervised process based on the highest cosine scores with the training face image vectors. The proposed method achieves a relative improvement of 56% in terms of EER over the baseline system on Labeled Faces in the Wild (LFW) dataset. This has successfully narrowed down the performance gap between cosine and PLDA scoring systems.