# Transparency Techniques for Neural Networks trained on Writer Identification and Writer Verification

arXiv: https://arxiv.org/abs/2506.16331 · HTML: https://mlsanity.com/paper/2506.16331/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 19 Jun 2025.

## Builds on (most cited first, 11 of 11)

- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [A Survey on Neural Network Interpretability](https://mlsanity.com/paper/2012.14261/) (2020)
- [Towards Explainable Artificial Intelligence](https://mlsanity.com/paper/1909.12072/) (2019)
- [Deep TEN: Texture Encoding Network](https://mlsanity.com/paper/1612.02844/) (2016)
- [SigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification](https://mlsanity.com/paper/1707.02131/) (2017)
- [Visual Explanation for Deep Metric Learning](https://mlsanity.com/paper/1909.12977/) (2019)
- [Writer Identification and Writer Retrieval Based on NetVLAD with Re-ranking](https://mlsanity.com/paper/2012.06186/) (2020)
- [Do Different Deep Metric Learning Losses Lead to Similar Learned Features?](https://mlsanity.com/paper/2205.02698/) (2022)
- [An Empirical Study on Writer Identification & Verification from Intra-variable Individual Handwriting](https://mlsanity.com/paper/1708.03361/) (2017)
- [Towards Visually Explaining Similarity Models](https://mlsanity.com/paper/2008.06035/) (2020)

## Abstract (arXiv)

Neural Networks are the state of the art for many tasks in the computer vision domain, including Writer Identification (WI) and Writer Verification (WV). The transparency of these "black box" systems is important for improvements of performance and reliability. For this work, two transparency techniques are applied to neural networks trained on WI and WV for the first time in this domain. The first technique provides pixel-level saliency maps, while the point-specific saliency maps of the second technique provide information on similarities between two images. The transparency techniques are evaluated using deletion and insertion score metrics. The goal is to support forensic experts with information on similarities in handwritten text and to explore the characteristics selected by a neural network for the identification process. For the qualitative evaluation, the highlights of the maps are compared to the areas forensic experts consider during the identification process. The evaluation results show that the pixel-wise saliency maps outperform the point-specific saliency maps and are suitable for the support of forensic experts.