# Beyond Fully Supervised Pixel Annotations: Scribble-Driven Weakly-Supervised Framework for Image Manipulation Localization

arXiv: https://arxiv.org/abs/2507.13018 · HTML: https://mlsanity.com/paper/2507.13018/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 17 Jul 2025.

## Builds on (most cited first, 16 of 16)

- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [Fighting Fake News: Image Splice Detection via Learned Self-Consistency](https://mlsanity.com/paper/1805.04096/) (2018)
- [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)
- [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)
- [Weakly-Supervised Camouflaged Object Detection with Scribble Annotations](https://mlsanity.com/paper/2207.14083/) (2022)
- [IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization](https://mlsanity.com/paper/2406.10580/) (2024)
- [Gated CRF Loss for Weakly Supervised Semantic Image Segmentation](https://mlsanity.com/paper/1906.04651/) (2019)
- [Mesoscopic Insights: Orchestrating Multi-scale & Hybrid Architecture for Image Manipulation Localization](https://mlsanity.com/paper/2412.13753/) (2024)
- [Pixel-Inconsistency Modeling for Image Manipulation Localization](https://mlsanity.com/paper/2310.00234/) (2023)
- [Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer](https://mlsanity.com/paper/2412.14598/) (2024)
- [Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning](https://mlsanity.com/paper/2309.01246/) (2023)
- [Unsupervised domain adaptation semantic segmentation of high-resolution remote sensing imagery with invariant domain-level prototype memory](https://mlsanity.com/paper/2208.07722/) (2022)

## Built on by (most cited first, 3 of 3)

- [Boosting Active Defense Persistence: A Two-Stage Defense Framework Combining Interruption and Poisoning Against Deepfake](https://mlsanity.com/paper/2508.07795/) (2025)
- [From Passive Perception to Active Memory: A Weakly Supervised Image Manipulation Localization Framework Driven by Coarse-Grained Annotations](https://mlsanity.com/paper/2511.20359/) (2025)
- [The Courtroom Trial of Pixels: Robust Image Manipulation Localization via Adversarial Evidence and Reinforcement Learning Judgment](https://mlsanity.com/paper/2604.14703/) (2026)

## Abstract (arXiv)

Deep learning-based image manipulation localization (IML) methods have achieved remarkable performance in recent years, but typically rely on large-scale pixel-level annotated datasets. To address the challenge of acquiring high-quality annotations, some recent weakly supervised methods utilize image-level labels to segment manipulated regions. However, the performance is still limited due to insufficient supervision signals. In this study, we explore a form of weak supervision that improves the annotation efficiency and detection performance, namely scribble annotation supervision. We re-annotate mainstream IML datasets with scribble labels and propose the first scribble-based IML (Sc-IML) dataset. Additionally, we propose the first scribble-based weakly supervised IML framework. Specifically, we employ self-supervised training with a structural consistency loss to encourage the model to produce consistent predictions under multi-scale and augmented inputs. In addition, we propose a prior-aware feature modulation module (PFMM) that adaptively integrates prior information from both manipulated and authentic regions for dynamic feature adjustment, further enhancing feature discriminability and prediction consistency in complex scenes. We also propose a gated adaptive fusion module (GAFM) that utilizes gating mechanisms to regulate information flow during feature fusion, guiding the model toward emphasizing potential manipulated regions. Finally, we propose a confidence-aware entropy minimization loss (L_ CEM ). This loss dynamically regularizes predictions in weakly annotated or unlabeled regions based on model uncertainty, effectively suppressing unreliable predictions. Experimental results show that our method outperforms existing fully supervised approaches in terms of average performance both in-distribution and out-of-distribution.