Fusion Transformer with Object Mask Guidance for Image Forgery Analysis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00379884" target="_blank" >RIV/68407700:21230/24:00379884 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/CVPRW63382.2024.00438" target="_blank" >https://doi.org/10.1109/CVPRW63382.2024.00438</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPRW63382.2024.00438" target="_blank" >10.1109/CVPRW63382.2024.00438</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Fusion Transformer with Object Mask Guidance for Image Forgery Analysis

Popis výsledku v původním jazyce

In this work we introduce OMG-Fuser a fusion transformer-based network designed to extract information from various forensic signals to enable robust image forgery detection and localization. Our approach can operate with an arbitrary number of forensic signals and leverages object information for their analysis -- unlike previous methods that rely on fusion schemes with few signals and often disregard image semantics. To this end we design a forensic signal stream composed of a transformer guided by an object attention mechanism associating patches that depict the same objects. In that way we incorporate object-level information from the image. Each forensic signal is processed by a different stream that adapts to its peculiarities. A token fusion transformer efficiently aggregates the outputs of an arbitrary number of network streams and generates a fused representation for each image patch. % These representations are finally processed by a long-range dependencies transformer that captures the intrinsic relations between the image patches. We assess two fusion variants on top of the proposed approach: (i) score-level fusion that fuses the outputs of multiple image forensics algorithms and (ii) feature-level fusion that fuses low-level forensic traces directly. Both variants exceed state-of-the-art performance on seven datasets for image forgery detection and localization with a relative average improvement of 12.1% and 20.4% in terms of F1. Our model is robust against traditional and novel forgery attacks and can be expanded with new signals without training from scratch. Our code is publicly available at: https://github.com/mever-team/omgfuser

Název v anglickém jazyce

Fusion Transformer with Object Mask Guidance for Image Forgery Analysis

Popis výsledku anglicky

In this work we introduce OMG-Fuser a fusion transformer-based network designed to extract information from various forensic signals to enable robust image forgery detection and localization. Our approach can operate with an arbitrary number of forensic signals and leverages object information for their analysis -- unlike previous methods that rely on fusion schemes with few signals and often disregard image semantics. To this end we design a forensic signal stream composed of a transformer guided by an object attention mechanism associating patches that depict the same objects. In that way we incorporate object-level information from the image. Each forensic signal is processed by a different stream that adapts to its peculiarities. A token fusion transformer efficiently aggregates the outputs of an arbitrary number of network streams and generates a fused representation for each image patch. % These representations are finally processed by a long-range dependencies transformer that captures the intrinsic relations between the image patches. We assess two fusion variants on top of the proposed approach: (i) score-level fusion that fuses the outputs of multiple image forensics algorithms and (ii) feature-level fusion that fuses low-level forensic traces directly. Both variants exceed state-of-the-art performance on seven datasets for image forgery detection and localization with a relative average improvement of 12.1% and 20.4% in terms of F1. Our model is robust against traditional and novel forgery attacks and can be expanded with new signals without training from scratch. Our code is publicly available at: https://github.com/mever-team/omgfuser

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GM21-28830M" target="_blank" >GM21-28830M: Učení Univerzální Vizuální Reprezentace s Omezenou Supervizí</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

ISBN

979-8-3503-6547-4

ISSN

2160-7508

e-ISSN

2160-7516

Počet stran výsledku

11

Strana od-do

4345-4355

Název nakladatele

IEEE Computer Society

Místo vydání

Los Alamitos

Místo konání akce

Seattle

Datum konání akce

16. 6. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001327781704051