Guardado en:
Detalles Bibliográficos
Autores principales: Yadav, Ankit, Vishwakarma, Dinesh Kumar
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2401.06995
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911756962496512
author Yadav, Ankit
Vishwakarma, Dinesh Kumar
author_facet Yadav, Ankit
Vishwakarma, Dinesh Kumar
contents Image splice manipulation presents a severe challenge in today's society. With easy access to image manipulation tools, it is easier than ever to modify images that can mislead individuals, organizations or society. In this work, a novel, "Visually Attentive Splice Localization Network with Multi-Domain Feature Extractor and Multi-Receptive Field Upsampler" has been proposed. It contains a unique "visually attentive multi-domain feature extractor" (VA-MDFE) that extracts attentional features from the RGB, edge and depth domains. Next, a "visually attentive downsampler" (VA-DS) is responsible for fusing and downsampling the multi-domain features. Finally, a novel "visually attentive multi-receptive field upsampler" (VA-MRFU) module employs multiple receptive field-based convolutions to upsample attentional features by focussing on different information scales. Experimental results conducted on the public benchmark dataset CASIA v2.0 prove the potency of the proposed model. It comfortably beats the existing state-of-the-arts by achieving an IoU score of 0.851, pixel F1 score of 0.9195 and pixel AUC score of 0.8989.
format Preprint
id arxiv_https___arxiv_org_abs_2401_06995
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Visually Attentive Splice Localization Network with Multi-Domain Feature Extractor and Multi-Receptive Field Upsampler
Yadav, Ankit
Vishwakarma, Dinesh Kumar
Computer Vision and Pattern Recognition
Image splice manipulation presents a severe challenge in today's society. With easy access to image manipulation tools, it is easier than ever to modify images that can mislead individuals, organizations or society. In this work, a novel, "Visually Attentive Splice Localization Network with Multi-Domain Feature Extractor and Multi-Receptive Field Upsampler" has been proposed. It contains a unique "visually attentive multi-domain feature extractor" (VA-MDFE) that extracts attentional features from the RGB, edge and depth domains. Next, a "visually attentive downsampler" (VA-DS) is responsible for fusing and downsampling the multi-domain features. Finally, a novel "visually attentive multi-receptive field upsampler" (VA-MRFU) module employs multiple receptive field-based convolutions to upsample attentional features by focussing on different information scales. Experimental results conducted on the public benchmark dataset CASIA v2.0 prove the potency of the proposed model. It comfortably beats the existing state-of-the-arts by achieving an IoU score of 0.851, pixel F1 score of 0.9195 and pixel AUC score of 0.8989.
title A Visually Attentive Splice Localization Network with Multi-Domain Feature Extractor and Multi-Receptive Field Upsampler
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.06995