检索结果-内蒙古大学图书馆

MSF-Net: Multi-stream fusion network for image manipulation detection and localization

DIGITAL SIGNAL PROCESSING 2025年 161卷

作者： Dou, Liyun Chen, Meng Qiu, Jiaqing Wang, Jin Nantong Univ Sch Artificial Intelligence & Comp Sci Nantong 226019 Jiangsu Peoples R China

Malicious image manipulation poses severe consequences, yet existing methods often lack robustness and struggle to handle complex manipulation scenarios. To overcome these limitations, we propose a multi-stream fusion network (MSF-Net) for image manipulation detection and localization. MSF-Net is an innovative three-stream parallel framework designed to enhance robustness and accuracy by integrating complementary features from the YCrCb color space, frequency domain (DCT stream), and noise domain. The network preprocesses data using YCrCb color space transformation and SRM filter kernel rotation, enabling it to capture detailed color and noise features. We conduct targeted feature extraction for each stream and fuse the extracted multidimensional features. A Multi-Stage Attention Module (MSAM) is utilized during the fusion phase to extract key information from the spatial, frequency, and noise domains, allowing the network to handle diverse manipulation attacks more effectively. The inclusion of the frequency domain stream in the network architecture markedly enhances the sensitivity of model to boundary artifacts and subtle manipulations. This enhances its generalization capabilities and provides strong robustness against common image processing operations such as JPEG compression and Gaussian blurring. Experimental results indicate that MSF-Net achieves outstanding performance in both manipulation detection and localization, especially in addressing complex manipulation types and diverse image processing operations. The parameter count and computational cost were effectively controlled through weight sharing and redundant feature elimination, allowing the model to achieve high performance within limited computational resources.

关键词： image manipulation detection and localization Deep learning Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Weakly-supervised cross-contrastive learning network for image manipulation detection and localization

引用

KNOWLEDGE-BASED SYSTEMS 2025年 310卷

作者： Bai, Ruyi Shanxi Univ Coll Automat & Software Taiyuan 030006 Shanxi Peoples R China

With the significant reduction in the cost of image manipulation due to advancements in image editing tools, it is crucial to investigate methods for detecting image manipulation. Currently, mainstream methods are based on various types of deep learning models, which have achieved some success. However, these models largely rely on pixel-level ground truth annotations for supervision, leading to an increase in image-level false positives due to limited real images. Obtaining GT annotations is time-consuming and labor-intensive, and the supervised model has a high demand for tampering mask. To address these limitations, we propose a Weakly-Supervised CrossContrastive Learning (WSCCL) network that can detect and locate image manipulation based solely on imagelevel labels ('real'/'tampered'). Specifically, we first leverage a dual-stream encoder-decoder architecture to extract visual and noise features separately and generate corresponding prediction distribution maps. We then adopt an adaptive approach to fuse prediction distribution maps, obtaining weakly-supervised pseudo-label. We design the Cross-Contrastive Learning Module(CCLM) using different aggregation methods for different layer features in the encoder, and apply cross-contrastive learning for the fusion features and the predicted features maps generated by the decoder. Finally, WSCCL compares the similarity between the reconstructed image obtained from the decoder and the predicted distribution map to make the pseudo-label closer to the real GT. Furthermore, extensive experiments confirm that our approach based on weakly supervised learning is comparable to supervised learning, both at the image-level and pixel-level. WSCCL exhibits strong adaptability to various types of manipulation and high resistance to attacks. This study demonstrates that our weakly supervised learning method can compete fully with supervised learning, regardless of the level of manipulation or annotation.

关键词： Weakly-supervised image manipulation detection and localization Cross-contrastive learning

来源：评论

学校读者我要写书评

暂无评论

HFDA-Net: Utilizing High-Frequency Feature and Dual-Attention to Enhance image manipulation detection and localization 33rd

HFDA-Net: Utilizing High-Frequency Feature and Dual-Attentio...

引用

33rd International Conference on Artificial Neural Networks and Machine Learning (ICANN)

作者： Liu, Chengeng Chen, Xu Xu, Tian Jia, Xiangyang Wuhan Univ Sch Comp Sci Wuhan Peoples R China

ISBN: (纸本)9783031723346;9783031723353

In this paper, we propose HFDA-Net, a novel approach for image manipulation detection and localization (IMDL) tasks. Unlike existing methods that only extract high-frequency features from the input image, HFDA-Net further extracts high-frequency features from RGB feature maps, capturing richer manipulation traces. In addition, HFDA-Net introduces a new module that efficiently calculates and combines position and channel attention, improving the accuracy and efficiency of manipulated region localization. Moreover, HFDA-Net supports feature extraction and aggregation at multiple scales and employs a coarse-to-fine pattern to predict manipulated regions, demonstrating remarkable generalizability. Thanks to its lightweight architecture, HFDA-Net achieves a processing speed of 65+ FPS when handling 1080P images. Extensive experiments on four image forensics benchmarks demonstrate that HFDA-Net generally outperforms existing advanced methods in manipulation detection by 1% to 15% and in manipulation localization by 1.5% to 5.4% under AUC. Furthermore, HFDA-Net exhibits good robustness compared to existing methods.

关键词： image manipulation detection and localization Multi-scale learning High-frequency feature Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

PSCC-Net: Progressive Spatio-Channel Correlation Network for image manipulation detection and localization

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2022年第11期32卷 7505-7517页

作者： Liu, Xiaohong Liu, Yaojie Chen, Jun Liu, Xiaoming McMaster Univ Dept Elect & Comp Engn Hamilton ON L8S 4K1 Canada Shanghai Jiao Tong Univ John Hoperoft Ctr Shanghai 200240 Peoples R China Michigan State Univ Dept Comp Sci & Engn E Lansing MI 48824 USA Google Res Mountain View CA 94043 USA

To defend against manipulation of image content, such as splicing, copy-move, and removal, we develop a Progressive Spatio-Channel Correlation Network (PSCC-Net) to detect and localize image manipulations. PSCC-Net processes the image in a two-path procedure: a top-down path that extracts local and global features and a bottom-up path that detects whether the input image is manipulated, and estimates its manipulation masks at multiple scales, where each mask is conditioned on the previous one. Different from the conventional encoder-decoder and no-pooling structures, PSCC-Net leverages features at different scales with dense crass-connections to produce manipulation masks in a coarse-to-fine fashion. Moreover, a Spatio-Channel Correlation Module (SCCM) captures both spatial and channel-wise correlations in the bottom-up path, which endows features with holistic cues, enabling the network to cope with a wide range of manipulation attacks. Thanks to the light-weight backbone and progressive mechanism, PSCC-Net can process 1, 080P images at 50+ FPS. Extensive experiments demonstrate the superiority of PSCC-Net over the state-of-the-art methods on both detection and localization. Codes and models are available at https://***/proteus1991/PSCC-Net.

关键词： image manipulation detection and localization progressive mechanism attention mechanism

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：