GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization
| Title: | GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization |
|---|---|
| Authors: | Chen, Yirui, Huang, Xudong, Zhang, Quan, Li, Wei, Zhu, Mingjian, Yan, Qiangyu, Li, Simiao, Chen, Hanting, Hu, Hailin, Yang, Jie, Liu, Wei, Hu, Jie |
| Publication Year: | 2024 |
| Collection: | Computer Science |
| Subject Terms: | Computer Science - Computer Vision and Pattern Recognition |
| More Details: | The extraordinary ability of generative models emerges as a new trend in image editing and generating realistic images, posing a serious threat to the trustworthiness of multimedia data and driving the research of image manipulation detection and location (IMDL). However, the lack of a large-scale data foundation makes the IMDL task unattainable. In this paper, we build a local manipulation data generation pipeline that integrates the powerful capabilities of SAM, LLM, and generative models. Upon this basis, we propose the GIM dataset, which has the following advantages: 1) Large scale, GIM includes over one million pairs of AI-manipulated images and real images. 2) Rich image content, GIM encompasses a broad range of image classes. 3) Diverse generative manipulation, the images are manipulated images with state-of-the-art generators and various manipulation tasks. The aforementioned advantages allow for a more comprehensive evaluation of IMDL methods, extending their applicability to diverse images. We introduce the GIM benchmark with two settings to evaluate existing IMDL methods. In addition, we propose a novel IMDL framework, termed GIMFormer, which consists of a ShadowTracer, Frequency-Spatial block (FSB), and a Multi-Window Anomalous Modeling (MWAM) module. Extensive experiments on the GIM demonstrate that GIMFormer surpasses the previous state-of-the-art approach on two different benchmarks. Comment: Code page: https://github.com/chenyirui/GIM |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/2406.16531 |
| Accession Number: | edsarx.2406.16531 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2406.16531 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20240624&spage=&pages=&title=GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization&atitle=GIM%3A%20A%20Million-scale%20Benchmark%20for%20Generative%20Image%20Manipulation%20Detection%20and%20Localization&aulast=Chen%2C%20Yirui&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2406.16531 RelevancyScore: 1098 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1098.04528808594 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Chen%2C+Yirui%22">Chen, Yirui</searchLink><br /><searchLink fieldCode="AR" term="%22Huang%2C+Xudong%22">Huang, Xudong</searchLink><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Quan%22">Zhang, Quan</searchLink><br /><searchLink fieldCode="AR" term="%22Li%2C+Wei%22">Li, Wei</searchLink><br /><searchLink fieldCode="AR" term="%22Zhu%2C+Mingjian%22">Zhu, Mingjian</searchLink><br /><searchLink fieldCode="AR" term="%22Yan%2C+Qiangyu%22">Yan, Qiangyu</searchLink><br /><searchLink fieldCode="AR" term="%22Li%2C+Simiao%22">Li, Simiao</searchLink><br /><searchLink fieldCode="AR" term="%22Chen%2C+Hanting%22">Chen, Hanting</searchLink><br /><searchLink fieldCode="AR" term="%22Hu%2C+Hailin%22">Hu, Hailin</searchLink><br /><searchLink fieldCode="AR" term="%22Yang%2C+Jie%22">Yang, Jie</searchLink><br /><searchLink fieldCode="AR" term="%22Liu%2C+Wei%22">Liu, Wei</searchLink><br /><searchLink fieldCode="AR" term="%22Hu%2C+Jie%22">Hu, Jie</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2024 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Computer+Vision+and+Pattern+Recognition%22">Computer Science - Computer Vision and Pattern Recognition</searchLink> – Name: Abstract Label: Description Group: Ab Data: The extraordinary ability of generative models emerges as a new trend in image editing and generating realistic images, posing a serious threat to the trustworthiness of multimedia data and driving the research of image manipulation detection and location (IMDL). However, the lack of a large-scale data foundation makes the IMDL task unattainable. In this paper, we build a local manipulation data generation pipeline that integrates the powerful capabilities of SAM, LLM, and generative models. Upon this basis, we propose the GIM dataset, which has the following advantages: 1) Large scale, GIM includes over one million pairs of AI-manipulated images and real images. 2) Rich image content, GIM encompasses a broad range of image classes. 3) Diverse generative manipulation, the images are manipulated images with state-of-the-art generators and various manipulation tasks. The aforementioned advantages allow for a more comprehensive evaluation of IMDL methods, extending their applicability to diverse images. We introduce the GIM benchmark with two settings to evaluate existing IMDL methods. In addition, we propose a novel IMDL framework, termed GIMFormer, which consists of a ShadowTracer, Frequency-Spatial block (FSB), and a Multi-Window Anomalous Modeling (MWAM) module. Extensive experiments on the GIM demonstrate that GIMFormer surpasses the previous state-of-the-art approach on two different benchmarks.<br />Comment: Code page: https://github.com/chenyirui/GIM – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2406.16531" linkWindow="_blank">http://arxiv.org/abs/2406.16531</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2406.16531 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2406.16531 |
| RecordInfo | BibRecord: BibEntity: Subjects: – SubjectFull: Computer Science - Computer Vision and Pattern Recognition Type: general Titles: – TitleFull: GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Chen, Yirui – PersonEntity: Name: NameFull: Huang, Xudong – PersonEntity: Name: NameFull: Zhang, Quan – PersonEntity: Name: NameFull: Li, Wei – PersonEntity: Name: NameFull: Zhu, Mingjian – PersonEntity: Name: NameFull: Yan, Qiangyu – PersonEntity: Name: NameFull: Li, Simiao – PersonEntity: Name: NameFull: Chen, Hanting – PersonEntity: Name: NameFull: Hu, Hailin – PersonEntity: Name: NameFull: Yang, Jie – PersonEntity: Name: NameFull: Liu, Wei – PersonEntity: Name: NameFull: Hu, Jie IsPartOfRelationships: – BibEntity: Dates: – D: 24 M: 06 Type: published Y: 2024 |
| ResultId | 1 |