# Exploring Complementarity and Explainability in CNNs for Periocular Verification Across Acquisition Distances

arXiv: https://arxiv.org/abs/2510.26282 · HTML: https://mlsanity.com/paper/2510.26282/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 30 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [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)
- [CNN Features off-the-shelf: an Astounding Baseline for Recognition](https://mlsanity.com/paper/1403.6382/) (2014)
- [WebFace260M: A Benchmark for Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2204.10149/) (2022)
- [A survey of face recognition techniques under occlusion](https://mlsanity.com/paper/2006.11366/) (2020)
- [A Comprehensive Overview of Biometric Fusion](https://mlsanity.com/paper/1902.02919/) (2019)
- [Periocular Recognition Using CNN Features Off-the-Shelf](https://mlsanity.com/paper/1809.06157/) (2018)
- [Ocular Recognition Databases and Competitions: A Survey](https://mlsanity.com/paper/1911.09646/) (2019)
- [On the Effect of Selfie Beautification Filters on Face Detection and Recognition](https://mlsanity.com/paper/2110.08934/) (2021)
- [Periocular Biometrics and its Relevance to Partially Masked Faces: A Survey](https://mlsanity.com/paper/2203.15203/) (2022)
- [Periocular Biometrics: A Modality for Unconstrained Scenarios](https://mlsanity.com/paper/2212.13792/) (2022)
- [Cross-Sensor Periocular Biometrics in a Global Pandemic: Comparative Benchmark and Novel Multialgorithmic Approach](https://mlsanity.com/paper/1902.08123/) (2019)
- [SqueezeFacePoseNet: Lightweight Face Verification Across Different Poses for Mobile Platforms](https://mlsanity.com/paper/2007.08566/) (2020)
- [A New Periocular Dataset Collected by Mobile Devices in Unconstrained Scenarios](https://mlsanity.com/paper/2011.12427/) (2020)
- [Cross-Spectral Periocular Recognition with Conditional Adversarial Networks](https://mlsanity.com/paper/2008.11604/) (2020)
- [An Explainable Model-Agnostic Algorithm for CNN-based Biometrics Verification](https://mlsanity.com/paper/2307.13428/) (2023)
- [Combined CNN and ViT features off-the-shelf: Another astounding baseline for recognition](https://mlsanity.com/paper/2407.19472/) (2024)
- [Selfie Periocular Verification using an Efficient Super-Resolution Approach](https://mlsanity.com/paper/2102.08449/) (2021)
- [Compact multi-scale periocular recognition using SAFE features](https://mlsanity.com/paper/2210.09778/) (2022)

## Abstract (arXiv)

We study the complementarity of different CNNs for periocular verification at different distances on the UBIPr database. We train three architectures of increasing complexity (SqueezeNet, MobileNetv2, and ResNet50) on a large set of eye crops from VGGFace2. We analyse performance with cosine and chi2 metrics, compare different network initialisations, and apply score-level fusion via logistic regression. In addition, we use LIME heatmaps and Jensen-Shannon divergence to compare attention patterns of the CNNs. While ResNet50 consistently performs best individually, the fusion provides substantial gains, especially when combining all three networks. Heatmaps show that networks usually focus on distinct regions of a given image, which explains their complementarity. Our method significantly outperforms previous works on UBIPr, achieving a new state-of-the-art.