Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2312.14395 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909096140079104 |
|---|---|
| author | Solomon, Enoch Woubie, Abraham Emiru, Eyael Solomon |
| author_facet | Solomon, Enoch Woubie, Abraham Emiru, Eyael Solomon |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_14395 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Unsupervised Deep Learning Image Verification Method Solomon, Enoch Woubie, Abraham Emiru, Eyael Solomon Computer Vision and Pattern Recognition Artificial Intelligence Computers and Society 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. |
| title | Unsupervised Deep Learning Image Verification Method |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2312.14395 |