# Unsupervised Feature Learning for Writer Identification and Writer Retrieval

arXiv: https://arxiv.org/abs/1705.09369 · HTML: https://mlsanity.com/paper/1705.09369/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2017.

## Built on by (most cited first, 24 of 24)

- [WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models](https://mlsanity.com/paper/2303.16576/) (2023)
- [A Survey of Historical Document Image Datasets](https://mlsanity.com/paper/2203.08504/) (2022)
- [GR-RNN: Global-Context Residual Recurrent Neural Networks for Writer Identification](https://mlsanity.com/paper/2104.05036/) (2021)
- [Writer Retrieval and Writer Identification in Greek Papyri](https://mlsanity.com/paper/2212.07664/) (2022)
- [Towards Writer Retrieval for Historical Datasets](https://mlsanity.com/paper/2305.05358/) (2023)
- [SAGHOG: Self-Supervised Autoencoder for Generating HOG Features for Writer Retrieval](https://mlsanity.com/paper/2404.17221/) (2024)
- [Self-Supervised Vision Transformers for Writer Retrieval](https://mlsanity.com/paper/2409.00751/) (2024)
- [Feature Mixing for Writer Retrieval and Identification on Papyri Fragments](https://mlsanity.com/paper/2306.12939/) (2023)
- [Siamese based Neural Network for Offline Writer Identification on word level data](https://mlsanity.com/paper/2211.14443/) (2022)
- [KaiRacters: Character-level-based Writer Retrieval for Greek Papyri](https://mlsanity.com/paper/2407.07536/) (2024)
- [Offline Text-Independent Writer Identification based on word level data](https://mlsanity.com/paper/2202.10207/) (2022)
- [Exploring the Open World Using Incremental Extreme Value Machines](https://mlsanity.com/paper/2205.14892/) (2022)
- [A Fair Evaluation of Various Deep Learning-Based Document Image Binarization Approaches](https://mlsanity.com/paper/2401.11831/) (2024)
- [Attention based End to end network for Offline Writer Identification on Word level data](https://mlsanity.com/paper/2404.07602/) (2024)
- [Structured Analysis and Comparison of Alphabets in Historical Handwritten Ciphers](https://mlsanity.com/paper/2410.21913/) (2024)
- [Online Writer Retrieval with Chinese Handwritten Phrases: A Synergistic Temporal-Frequency Representation Learning Approach](https://mlsanity.com/paper/2412.11668/) (2024)
- [Towards the Influence of Text Quantity on Writer Retrieval](https://mlsanity.com/paper/2506.07566/) (2025)
- [Global Regular Network for Writer Identification](https://mlsanity.com/paper/2201.05951/) (2022)
- [Recognizing Handwriting Styles in a Historical Scanned Document Using Unsupervised Fuzzy Clustering](https://mlsanity.com/paper/2210.16780/) (2022)
- [Assessing the impact of Binarization for Writer Identification in Greek Papyrus](https://mlsanity.com/paper/2506.15852/) (2025)
- [Beyond the Pipeline: Analyzing Key Factors in End-to-End Deep Learning for Historical Writer Identification](https://mlsanity.com/paper/2510.18671/) (2025)
- [Bag of Bags: Adaptive Visual Vocabularies for Genizah Join Image Retrieval](https://mlsanity.com/paper/2604.08138/) (2026)
- [BullingerDB: A Dataset for Handwritten Text Recognition and Writer Retrieval](https://mlsanity.com/paper/2605.30235/) (2026)
- [Handwriting Extraction and Analysis of Signature Lists in Swiss Popular Initiatives](https://mlsanity.com/paper/2606.05018/) (2026)

## Abstract (arXiv)

Deep Convolutional Neural Networks (CNN) have shown great success in supervised classification tasks such as character classification or dating. Deep learning methods typically need a lot of annotated training data, which is not available in many scenarios. In these cases, traditional methods are often better than or equivalent to deep learning methods. In this paper, we propose a simple, yet effective, way to learn CNN activation features in an unsupervised manner. Therefore, we train a deep residual network using surrogate classes. The surrogate classes are created by clustering the training dataset, where each cluster index represents one surrogate class. The activations from the penultimate CNN layer serve as features for subsequent classification tasks. We evaluate the feature representations on two publicly available datasets. The focus lies on the ICDAR17 competition dataset on historical document writer identification (Historical-WI). We show that the activation features trained without supervision are superior to descriptors of state-of-the-art writer identification methods. Additionally, we achieve comparable results in the case of handwriting classification using the ICFHR16 competition dataset on historical Latin script types (CLaMM16).