# An Explainable Model-Agnostic Algorithm for CNN-based Biometrics Verification

arXiv: https://arxiv.org/abs/2307.13428 · HTML: https://mlsanity.com/paper/2307.13428/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 25 Jul 2023.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Probabilistic Face Embeddings](https://mlsanity.com/paper/1904.09658/) (2019)
- [Biometrics: Trust, but Verify](https://mlsanity.com/paper/2105.06625/) (2021)
- [Towards Interpretable Face Recognition](https://mlsanity.com/paper/1805.00611/) (2018)
- [A Survey on Periocular Biometrics Research](https://mlsanity.com/paper/1810.03360/) (2018)
- [Periocular Recognition Using CNN Features Off-the-Shelf](https://mlsanity.com/paper/1809.06157/) (2018)
- [How are attributes expressed in face DCNNs?](https://mlsanity.com/paper/1910.05657/) (2019)
- [MobiFace: A Lightweight Deep Learning Face Recognition on Mobile Devices](https://mlsanity.com/paper/1811.11080/) (2018)
- [Quality Measures in Biometric Systems](https://mlsanity.com/paper/2111.08704/) (2021)
- [SqueezeFacePoseNet: Lightweight Face Verification Across Different Poses for Mobile Platforms](https://mlsanity.com/paper/2007.08566/) (2020)
- [Explainability of the Implications of Supervised and Unsupervised Face Image Quality Estimations Through Activation Map Variation Analyses in Face Recognition Models](https://mlsanity.com/paper/2112.04827/) (2021)

## Built on by (most cited first, 4 of 4)

- [Combined CNN and ViT features off-the-shelf: Another astounding baseline for recognition](https://mlsanity.com/paper/2407.19472/) (2024)
- [Deep Network Pruning: A Comparative Study on CNNs in Face Recognition](https://mlsanity.com/paper/2405.18302/) (2024)
- [Exploring Complementarity and Explainability in CNNs for Periocular Verification Across Acquisition Distances](https://mlsanity.com/paper/2510.26282/) (2025)
- [Leveraging Large-Scale Face Datasets for Deep Periocular Recognition via Ocular Cropping](https://mlsanity.com/paper/2510.26294/) (2025)

## Abstract (arXiv)

This paper describes an adaptation of the Local Interpretable Model-Agnostic Explanations (LIME) AI method to operate under a biometric verification setting. LIME was initially proposed for networks with the same output classes used for training, and it employs the softmax probability to determine which regions of the image contribute the most to classification. However, in a verification setting, the classes to be recognized have not been seen during training. In addition, instead of using the softmax output, face descriptors are usually obtained from a layer before the classification layer. The model is adapted to achieve explainability via cosine similarity between feature vectors of perturbated versions of the input image. The method is showcased for face biometrics with two CNN models based on MobileNetv2 and ResNet50.