# Weakly-Supervised Image Forgery Localization via Vision-Language Collaborative Reasoning Framework

arXiv: https://arxiv.org/abs/2508.01338 · HTML: https://mlsanity.com/paper/2508.01338/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 37 references that are in the map.
- First posted on arXiv 2 Aug 2025.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Simple and Deep Graph Convolutional Networks](https://mlsanity.com/paper/2007.02133/) (2020)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection](https://mlsanity.com/paper/2112.08935/) (2021)
- [Image Manipulation Detection by Multi-View Multi-Scale Supervision](https://mlsanity.com/paper/2104.06832/) (2021)
- [SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization](https://mlsanity.com/paper/2009.00726/) (2020)
- [Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries](https://mlsanity.com/paper/1903.02495/) (2019)
- [Fully Convolutional Multi-Class Multiple Instance Learning](https://mlsanity.com/paper/1412.7144/) (2014)
- [Constrained R-CNN: A general image manipulation detection model](https://mlsanity.com/paper/1911.08217/) (2019)
- [Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning](https://mlsanity.com/paper/2309.01246/) (2023)
- [Exploring Multi-view Pixel Contrast for General and Robust Image Forgery Localization](https://mlsanity.com/paper/2406.13565/) (2024)
- [Weakly-supervised Audio Temporal Forgery Localization via Progressive Audio-language Co-learning Network](https://mlsanity.com/paper/2505.01880/) (2025)
- [SUMI-IFL: An Information-Theoretic Framework for Image Forgery Localization with Sufficiency and Minimality Constraints](https://mlsanity.com/paper/2412.09981/) (2024)

## Built on by (most cited first, 4 of 4)

- [Edge-Enhanced Vision Transformer Framework for Accurate AI-Generated Image Detection](https://mlsanity.com/paper/2508.17877/) (2025)
- [CIEC: Coupling Implicit and Explicit Cues for Multimodal Weakly Supervised Manipulation Localization](https://mlsanity.com/paper/2602.02175/) (2026)
- [SegWave: Wavelet-Driven Segmentation of Tampered Regions](https://mlsanity.com/paper/2608.30714/) (2026)
- [Agents That Edit Documents: Measuring Agentic PDF Forgery Against a Non-Agentic Control](https://mlsanity.com/paper/2609.23953/) (2026)

## Abstract (arXiv)

Image forgery localization aims to precisely identify tampered regions within images, but it commonly depends on costly pixel-level annotations. To alleviate this annotation burden, weakly supervised image forgery localization (WSIFL) has emerged, yet existing methods still achieve limited localization performance as they mainly exploit intra-image consistency clues and lack external semantic guidance to compensate for weak supervision. In this paper, we propose ViLaCo, a vision-language collaborative reasoning framework that introduces auxiliary semantic supervision distilled from pre-trained vision-language models (VLMs), enabling accurate pixel-level localization using only image-level labels. Specifically, ViLaCo first incorporates semantic knowledge through a vision-language feature modeling network, which jointly extracts textual and visual priors using pre-trained VLMs. Next, an adaptive vision-language reasoning network aligns textual semantics and visual features through mutual interactions, producing semantically aligned representations. Subsequently, these representations are passed into dual prediction heads, where the coarse head performs image-level classification and the fine head generates pixel-level localization masks, thereby bridging the gap between weak supervision and fine-grained localization. Moreover, a contrastive patch consistency module is introduced to cluster tampered features while separating authentic ones, facilitating more reliable forgery discrimination. Extensive experiments on multiple public datasets demonstrate that ViLaCo substantially outperforms existing WSIFL methods, achieving state-of-the-art performance in both detection and localization accuracy.