Off-the-shelf Vision Models Benefit Image Manipulation Localization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910118576128000 |
|---|---|
| author | Zhang, Zhengxuan Song, Keji Hu, Junmin Luo, Ao Li, Yuezun |
| author_facet | Zhang, Zhengxuan Song, Keji Hu, Junmin Luo, Ao Li, Yuezun |
| contents | Image manipulation localization (IML) and general vision tasks are typically treated as two separate research directions due to the fundamental differences between manipulation-specific and semantic features. In this paper, however, we bridge this gap by introducing a fresh perspective: these two directions are intrinsically connected, and general semantic priors can benefit IML. Building on this insight, we propose a novel trainable adapter (named ReVi) that repurposes existing off-the-shelf general-purpose vision models (e.g., image generation and segmentation networks) for IML. Inspired by robust principal component analysis, the adapter disentangles semantic redundancy from manipulation-specific information embedded in these models and selectively enhances the latter. Unlike existing IML methods that require extensive model redesign and full retraining, our method relies on the off-the-shelf vision models with frozen parameters and only fine-tunes the proposed adapter. The experimental results demonstrate the superiority of our method, showing the potential for scalable IML frameworks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09096 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Off-the-shelf Vision Models Benefit Image Manipulation Localization Zhang, Zhengxuan Song, Keji Hu, Junmin Luo, Ao Li, Yuezun Computer Vision and Pattern Recognition Multimedia Image and Video Processing Image manipulation localization (IML) and general vision tasks are typically treated as two separate research directions due to the fundamental differences between manipulation-specific and semantic features. In this paper, however, we bridge this gap by introducing a fresh perspective: these two directions are intrinsically connected, and general semantic priors can benefit IML. Building on this insight, we propose a novel trainable adapter (named ReVi) that repurposes existing off-the-shelf general-purpose vision models (e.g., image generation and segmentation networks) for IML. Inspired by robust principal component analysis, the adapter disentangles semantic redundancy from manipulation-specific information embedded in these models and selectively enhances the latter. Unlike existing IML methods that require extensive model redesign and full retraining, our method relies on the off-the-shelf vision models with frozen parameters and only fine-tunes the proposed adapter. The experimental results demonstrate the superiority of our method, showing the potential for scalable IML frameworks. |
| title | Off-the-shelf Vision Models Benefit Image Manipulation Localization |
| topic | Computer Vision and Pattern Recognition Multimedia Image and Video Processing |
| url | https://arxiv.org/abs/2604.09096 |