Efficient Multi-Scale Feature Fusion for Image Manipulation Detection
Summary :
Convolutional Neural Network (CNN) has made extraordinary progress in image classification tasks. However, it is less effective to use CNN directly to detect image manipulation. To address this problem, we propose an image filtering layer and a multi-scale feature fusion module which can guide the model more accurately and effectively to perform image manipulation detection. Through a series of experiments, it is shown that our model achieves improvements on image manipulation detection compared with the previous researches.
- Publication
- IEICE TRANSACTIONS on Information Vol.E105-D No.5 pp.1107-1111
- Publication Date
- 2022/05/01
- Publicized
- 2022/02/03
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2021EDL8099
- Type of Manuscript
- LETTER
- Category
- Information Network
Authors
Yuxue ZHANG
Shanghai University
Guorui FENG
Shanghai University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yuxue ZHANG, Guorui FENG, "Efficient Multi-Scale Feature Fusion for Image Manipulation Detection" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 5, pp. 1107-1111, May 2022, doi: 10.1587/transinf.2021EDL8099.
Abstract: Convolutional Neural Network (CNN) has made extraordinary progress in image classification tasks. However, it is less effective to use CNN directly to detect image manipulation. To address this problem, we propose an image filtering layer and a multi-scale feature fusion module which can guide the model more accurately and effectively to perform image manipulation detection. Through a series of experiments, it is shown that our model achieves improvements on image manipulation detection compared with the previous researches.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDL8099/_p
Copy
@ARTICLE{e105-d_5_1107,
author={Yuxue ZHANG, Guorui FENG, },
journal={IEICE TRANSACTIONS on Information},
title={Efficient Multi-Scale Feature Fusion for Image Manipulation Detection},
year={2022},
volume={E105-D},
number={5},
pages={1107-1111},
abstract={Convolutional Neural Network (CNN) has made extraordinary progress in image classification tasks. However, it is less effective to use CNN directly to detect image manipulation. To address this problem, we propose an image filtering layer and a multi-scale feature fusion module which can guide the model more accurately and effectively to perform image manipulation detection. Through a series of experiments, it is shown that our model achieves improvements on image manipulation detection compared with the previous researches.},
keywords={},
doi={10.1587/transinf.2021EDL8099},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Efficient Multi-Scale Feature Fusion for Image Manipulation Detection
T2 - IEICE TRANSACTIONS on Information
SP - 1107
EP - 1111
AU - Yuxue ZHANG
AU - Guorui FENG
PY - 2022
DO - 10.1587/transinf.2021EDL8099
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2022
AB - Convolutional Neural Network (CNN) has made extraordinary progress in image classification tasks. However, it is less effective to use CNN directly to detect image manipulation. To address this problem, we propose an image filtering layer and a multi-scale feature fusion module which can guide the model more accurately and effectively to perform image manipulation detection. Through a series of experiments, it is shown that our model achieves improvements on image manipulation detection compared with the previous researches.
ER -
English
