# Efficient Document Tampering Localization with Multi-Level Discrepancy Features and Unified DCT-Quantization Embedding

arXiv: https://arxiv.org/abs/2606.22285 · HTML: https://mlsanity.com/paper/2606.22285/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 37 references that are in the map.
- First posted on arXiv 21 Jun 2026.

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

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (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)
- [Image Manipulation Detection by Multi-View Multi-Scale Supervision](https://mlsanity.com/paper/2104.06832/) (2021)
- [Editing Text in the Wild](https://mlsanity.com/paper/1908.03047/) (2019)
- [Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization](https://mlsanity.com/paper/2108.12947/) (2021)
- [IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer](https://mlsanity.com/paper/2307.14863/) (2023)
- [Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization](https://mlsanity.com/paper/2412.13753/) (2024)
- [ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization](https://mlsanity.com/paper/2505.11003/) (2025)
- [Revisiting Tampered Scene Text Detection in the Era of Generative AI](https://mlsanity.com/paper/2407.21422/) (2024)
- [Toward Real Text Manipulation Detection: New Dataset and New Solution](https://mlsanity.com/paper/2312.06934/) (2023)
- [Omni-IML: Towards Unified Image Manipulation Localization](https://mlsanity.com/paper/2411.14823/) (2024)
- [Leveraging Contrastive Learning for a Similarity-Guided Tampered Document Data Generation Pipeline](https://mlsanity.com/paper/2602.17322/) (2026)

## Abstract (arXiv)

Localizing document tampering is extremely challenging, as manipulations are crafted to appear visually consistent and often leave only subtle traces that are nearly invisible to the human eye. In prior work, evaluation has been largely dominated by synthetic benchmarks that closely match the training distribution, and methods have shown steady progress under this setting. However, these gains often translate poorly to human-made forgeries and to cross-domain evaluation, where both the source documents and the tampering pipeline can change, leading to a distribution shift. In addition, since the introduction of the Frequency Perception Head for the discrete cosine transform (DCT) modality, it has become a standard choice, and subsequent work has largely focused on downstream modules and fusion strategies rather than revisiting the backbone itself. To help close this gap in cross-domain performance and improve the DCT backbone design, we propose DiffNet, a relatively simple yet effective RGB--DCT early-fusion architecture driven by two key design choices. First, to ensure that the decoder aggregates multi-scale inconsistency evidence rather than operating on raw, content-heavy activations, we apply a lightweight multi-level discrepancy transformation at the output of each backbone stage, replacing features with magnitude-only responses to learned zero-sum filters. Second, we design an efficient DCT-domain backbone that relies on a lightweight frequency-index-aware DCT--quantization joint embedding. Our approach achieves state-of-the-art performance on cross-domain and human-made document tampering localization, outperforming prior methods by around 30%, with up to 7× higher throughput than the previous best model.