# Leveraging Contrastive Learning for a Similarity-Guided Tampered Document Data Generation Pipeline

arXiv: https://arxiv.org/abs/2602.17322 · HTML: https://mlsanity.com/paper/2602.17322/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 30 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Builds on (most cited first, 10 of 10)

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Building and better understanding vision-language models: insights and future directions](https://mlsanity.com/paper/2408.12637/) (2024)
- [AnyText: Multilingual Visual Text Generation And Editing](https://mlsanity.com/paper/2311.03054/) (2023)
- [PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2103.10596/) (2021)
- [TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization](https://mlsanity.com/paper/2212.10957/) (2022)
- [LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding](https://mlsanity.com/paper/2104.08836/) (2021)
- [Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2108.12947/) (2021)
- [FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing](https://mlsanity.com/paper/2505.03329/) (2025)
- [Toward Real Text Manipulation Detection: New Dataset and New Solution](https://mlsanity.com/paper/2312.06934/) (2023)
- [TNCR: Table Net Detection and Classification Dataset](https://mlsanity.com/paper/2106.15322/) (2021)

## Built on by (most cited first, 1 of 1)

- [Efficient Document Tampering Localization with Multi-Level Discrepancy Features and Unified DCT-Quantization Embedding](https://mlsanity.com/paper/2606.22285/) (2026)

## Abstract (arXiv)

Detecting tampered text in document images is a challenging task due to data scarcity. To address this, previous work has attempted to generate tampered documents using rule-based methods. However, the resulting documents often suffer from limited variety and poor visual quality, typically leaving highly visible artifacts that are rarely observed in real-world manipulations. This undermines the model's ability to learn robust, generalizable features and results in poor performance on real-world data. Motivated by this discrepancy, we propose a novel method for generating high-quality tampered document images. We first train an auxiliary network to compare text crops, leveraging contrastive learning with a novel strategy for defining positive pairs and their corresponding negatives. We also train a second auxiliary network to evaluate whether a crop tightly encloses the intended characters, without cutting off parts of characters or including parts of adjacent ones. Using a carefully designed generation pipeline that leverages both networks, we introduce a framework capable of producing diverse, high-quality tampered document images. We assess the effectiveness of our data generation pipeline by training multiple models on datasets derived from the same source images, generated using our method and existing approaches, under identical training protocols. Evaluating these models on various open-source datasets shows that our pipeline yields consistent performance improvements across architectures and datasets.