检索结果-内蒙古大学图书馆

CrossDiff: Exploring Self-Supervised Representation of Pansharpening via Cross-Predictive Diffusion Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xing, Yinghui Qu, Litao Zhang, Shizhou Zhang, Kai Zhang, Yanning Ran, Lingyan Zhang, Xiuwei Yin, Hanlin The Shaanxi Provincial Key Laboratory of Speech and Image Information Processing The National Engineering Laboratory for Integrated Aerospace-GroundOcean Big Data Application Technology School of Computer Science Northwestern Polytechnical University Xi’an710072 China The Research Development Institute Northwestern Polytechnical University in Shenzhen Shenzhen518057 China

Fusion of a panchromatic (PAN) image and corresponding multispectral (MS) image is also known as pansharpening, which aims to combine abundant spatial details of PAN and spectral information of MS. Due to the absence of high-resolution MS images, available deep-learning-based methods usually follow the paradigm of training at reduced resolution and testing at both reduced and full resolution. When taking original MS and PAN images as inputs, they always obtain sub-optimal results due to the scale variation. In this paper, we propose to explore the self-supervised representation of pansharpening by designing a cross-predictive diffusion model, named CrossDiff. It has two-stage training. In the first stage, we introduce a cross-predictive pretext task to pre-train the UNet structure based on conditional DDPM, while in the second stage, the encoders of the UNets are frozen to directly extract spatial and spectral features from PAN and MS, and only the fusion head is trained to adapt for pansharpening task. Extensive experiments show the effectiveness and superiority of the proposed model compared with state-of-the-art supervised and unsupervised methods. Besides, the cross-sensor experiments also verify the generalization ability of proposed self-supervised representation learners for other satellite’s datasets. We will release our code for reproducibility. © 2024, CC BY.

关键词： Deep learning

Onset Detection of Pulse-Shaped Bioelectrical Signals Using Linear State Space Models

学校读者我要写书评

暂无评论

Onset Detection of Pulse-Shaped Bioelectrical Signals Using ...

作者： Waldmann, Frédéric Baeriswyl, Christof Andonie, Raphael Wildhaber, Reto A. Institute for Medical Engineering and Medical Informatics University of Applied Sciences and Arts Northwestern Switzerland Muttenz Switzerland STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Leuven Belgium Bern University of Applied Sciences Biel Switzerland Hearing Research Laboratory ARTORG Center for Biomedical Engineering Research University of Bern Bern Switzerland Institute for Medical Engineering and Medical Informatics University of Applied Sciences and Arts Northwestern Switzerland Hofackerstrasse 30 Muttenz Switzerland ETH Zurich Sternwartstrasse 7 Zurich Switzerland

Bioelectrical signals are often pulse-shaped with superimposed interference signals. In this context, accurate identification of features such as pulse onsets, peaks, amplitudes, and duration is a frequent problem. In this paper, we present a versatile method of rather low computational complexity to robustly identify such features in real-world signals. For that, we take use of two straight-line models fit to the observations by minimizing a quadratic cost term, and then identify desired features by tweaked likelihood measures. To demonstrate the idea and facilitate access to the method, we provide examples from the field of cardiology. © 2022 The Author(s), published by De Gruyter.

关键词： Feature extraction

FELSDiff: Image Super-Resolution Based on Diffusion Model Fusing Feature Extraction with Latent Space

学校读者我要写书评

暂无评论

FELSDiff: Image Super-Resolution Based on Diffusion Model Fu...

International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Cancan Wu Zhi Zhang College of Computer Science and Technology Wuhan University of Science and Technology Wuhan Hubei China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan Hubei China

ISBN: (数字)9798350356328

ISBN: (纸本)9798350356335

In addressing issues like an excessive number of network parameters and the loss of fine texture details in image super-resolution reconstruction approaches based on diffusion models, this passage introduces a novel image super-resolution model (FELSDiff). This model relies on the fusion of diffusion models, feature extraction, and latent space. FELSDiff utilizes a Pre-trained CNN for initial super-resolution to extract the primary low-band features and part high-band features of the image. The preliminary super-resolved image is then concatenated as a condition to this model. We introduce a cross-attention mechanism guided by the high-band features of the preliminary super-resolved image to enhance the network's feature extraction capability and obtain more effective features. In the U-Net structure, we incorporate a latent space strategy, enabling the model's training and inference processes to be conducted in the latent space, thereby reducing the number of network parameters. Experimental results on multiple standard datasets indicate that this method outperforms other advanced methods overall.

关键词： Training Runtime Computational modeling Superresolution Memory management Feature extraction Diffusion models Convolutional neural networks Image reconstruction Standards

Localization of Dummy data Injection Attacks in Power Systems Considering Incomplete Topological Information: A Spatio-Temporal Graph Wavelet Convolutional Neural Network Approach

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Qu, Zhaoyang Dong, Yunchang Li, Yang Song, Siqi Jiang, Tao Li, Min Wang, Qiming Wang, Lei Bo, Xiaoyong School of Electrical Engineering Northeast Electric Power University Jilin China Jilin Electric Power Research Institute of State Grid Changchun China Northeast Electric Power Design and Institute Co. Ltd. China Power Engineering Consulting Group China Jilin Engineering Technology Research Center of Intelligent Electric Power Big Data Processing Jilin China

The emergence of new dummy data attacks seriously endangers power systems' safe and stable operation. Due to the injected data meeting the spatial distance concealment, it is difficult to accurately locate the attack location by existing methods, so a dummy data injection attack (DDIA) localization method based on a spatio-temporal graph wavelet convolutional neural network is proposed in this paper. First, the principle of the new DDIA for power systems is analyzed. Based on the injected data satisfying the constraints of consistency, virtuality, destructiveness, and finiteness, the mathematical model of DDIA under consideration of incomplete topological information and AC state estimation is designed from the attacker's perspective to compensate for the limitations of the DC flow-based attack data generation method that can be easily captured. Then, combining the a priori knowledge of grid topology, taking into account the temporal correlation of the measurement data and the topology-dependent features of the power grid, the temporal and spatial attention matrices are introduced to capture the spatio-temporal correlation of the attack adaptively, and the spatiotemporal features of DDIA are extracted jointly based on gated stacked causal convolution and graph wavelet sparse convolution, which improves the dynamic mining ability and computational efficiency of the spatiotemporal correlation in the neighborhood. Finally, based on the spatio-temporal graph neural network, a DDIA localization method is proposed to adapt to the topological structure changes of the power system. The correctness of the DDIA model is proved through the analysis of arithmetic cases. It is verified that the proposed localization method can detect and localize DDIA quickly and effectively and has superior accuracy, robustness and generalization ability. © 2023, The Authors. All rights reserved.

关键词： Convolution

StyleGene: Crossover and Mutation of Region-level Facial Genes for Kinship Face Synthesis

学校读者我要写书评

暂无评论

StyleGene: Crossover and Mutation of Region-level Facial Gen...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Hao Li Xianxu Hou Zepeng Huang Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

High-fidelity kinship face synthesis has many potential applications, such as kinship verification, missing child identification, and social media analysis. However, it is challenging to synthesize high-quality descendant faces with genetic relations due to the lack of large-scale, high-quality annotated kinship data. This paper proposes RFG (Region-level Facial Gene) extraction framework to address this issue. We propose to use IGE (Image-based Gene Encoder), LGE (Latent-based Gene Encoder) and Gene Decoder to learn the RFGs of a given face image, and the relationships between RFGs and the latent space of Style-GAN2. As cycle-like losses are designed to measure the $\mathcal{L}_{2}$ distances between the output of Gene Decoder and image encoder, and that between the output of LGE and IGE, only face images are required to train our framework, i.e. no paired kinship face data is required. Based upon the proposed RFGs, a crossover and mutation module is further designed to inherit the facial parts of parents. A Gene Pool has also been used to introduce the variations into the mutation of RFGs. The diversity of the faces of descendants can thus be significantly increased. Qualitative, quantitative, and subjective experiments on FIW, TSKinFace, and FF-databases clearly show that the quality and diversity of kinship faces generated by our approach are much better than the existing state-of-the-art methods.

关键词：

GM-DF: Generalized Multi-Scenario Deepfake Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lai, Yingxin Yu, Zitong Yang, Jing Li, Bin Kang, Xiangui Shen, Linlin The School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Information Security The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510080 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

Existing face forgery detection usually follows the paradigm of training models in a single domain, which leads to limited generalization capacity when unseen scenarios and unknown attacks occur. In this paper, we elaborately investigate the generalization capacity of deepfake detection models when jointly trained on multiple face forgery detection datasets. We first find a rapid degradation of detection accuracy when models are directly trained on combined datasets due to the discrepancy across collection scenarios and generation methods. To address the above issue, a Generalized Multi-Scenario Deepfake Detection framework (GM-DF) is proposed to serve multiple real-world scenarios by a unified model. First, we propose a hybrid expert modeling approach for domain-specific real/forgery feature extraction. Besides, as for the commonality representation, we use CLIP to extract the common features for better aligning visual and textual features across domains. Meanwhile, we introduce a masked image reconstruction mechanism to force models to capture rich forged details. Finally, we supervise the models via a domain-aware meta-learning strategy to further enhance their generalization capacities. Specifically, we design a novel domain alignment loss to strongly align the distributions of the meta-test domains and meta-train domains. Thus, the updated models are able to represent both specific and common real/forgery features across multiple datasets. In consideration of the lack of study of multi-dataset training, we establish a new benchmark leveraging multi-source data to fairly evaluate the models' generalization capacity on unseen scenarios. Both qualitative and quantitative experiments on five datasets conducted on traditional protocols as well as the proposed benchmark demonstrate the effectiveness of our approach. The codes will be available on https://***/laiyingxin2/GM-DF. Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

Deepfake Network Architecture Attribution

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Tianyun Huang, Ziyao Cao, Juan Li, Lei Li, Xirong Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

With the rapid progress of generation technology, it has become necessary to attribute the origin of fake images. Existing works on fake image attribution perform multi-class classification on several Generative Adversarial Network (GAN) models and obtain high accuracies. While encouraging, these works are restricted to model-level attribution, only capable of handling images generated by seen models with a specific seed, loss and dataset, which is limited in real-world scenarios when fake images may be generated by privately trained models. This motivates us to ask whether it is possible to attribute fake images to the source models’ architectures even if they are finetuned or retrained under different configurations. In this work, we present the first study on Deepfake Network Architecture Attribution to attribute fake images on architecture-level. Based on an observation that GAN architecture is likely to leave globally consistent fingerprints while traces left by model weights vary in different regions, we provide a simple yet effective solution named DNA-Det for this problem. Extensive experiments on multiple cross-test setups and a large-scale dataset demonstrate the effectiveness of DNA-Det. Our source code and dataset can be found here: https://***/ICTMCG/DNA-Det Copyright © 2022, The Authors. All rights reserved.

关键词： Network architecture

DRAG: Dynamic Region-Aware GCN for Privacy-Leaking Image Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Guang Cao, Juan Sheng, Qiang Qi, Peng Li, Xirong Li, Jintao Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

The daily practice of sharing images on social media raises a severe issue about privacy leakage. To address the issue, privacy-leaking image detection is studied recently, with the goal to automatically identify images that may leak privacy. Recent advance on this task benefits from focusing on crucial objects via pretrained object detectors and modeling their correlation. However, these methods have two limitations: 1) they neglect other important elements like scenes, textures, and objects beyond the capacity of pretrained object detectors;2) the correlation among objects is fixed, but a fixed correlation is not appropriate for all the images. To overcome the limitations, we propose the Dynamic Region-Aware Graph Convolutional Network (DRAG) that dynamically finds out crucial regions including objects and other important elements, and models their correlation adaptively for each input image. To find out crucial regions, we cluster spatially-correlated feature channels into several region-aware feature maps. Further, we dynamically model the correlation with the self-attention mechanism and explore the interaction among the regions with a graph convolutional network. The DRAG achieved an accuracy of 87% on the largest dataset for privacy-leaking image detection, which is 10 percentage points higher than the state of the art. The further case study demonstrates that it found out crucial regions containing not only objects but other important elements like textures. The code and more details are in https://***/guang-yanng/DRAG. © 2022, CC BY.

关键词： Object detection

A Novel Statistical Preprocessing Approach for Hyperspectral Image Unmixing

学校读者我要写书评

暂无评论

A Novel Statistical Preprocessing Approach for Hyperspectral...

2021 IEEE India Geoscience and Remote Sensing Symposium, InGARSS 2021

作者： Kowkabi, Fatemeh Keshavarz, Ahmad Kumar, Lalit Islamic Azad University College of Engineering Marvdasht Branch Department of Electrical Engineering Marvdasht Iran Persian Gulf University IoT and Signal Processing Research Group Ict Research Institute Faculty of Intelligent Systems Engineering and Data Science Bushehr*** Iran EastCoast Geospatial Consultants ArmidaleNSW2350 Australia

ISBN: (纸本)9781665442497

Hyperspectral images have wide application in different commercial and military missions. However, these images suffer from the low spatial resolution, and hence, spectral unmixing has been proposed as a suitable technique to solve this deficiency. Recently, some preprocessing modules have been proposed which use the combination of spatial and spectral information of image pixels with the purpose of improving endmember extraction and spectral unmixing in hyperspectral images. In this paper, we propose a statistical preprocessing algorithm using weighted extended cumulative entropy (WECE) as the Edge Detection algorithm to identify spectrally pure pixels and KL distance estimation using the mean and covariance values of pure oversegments and their neighbors to find the spatially homogenous and spectrally pure pixels for the next endmember extraction algorithms. Moreover, the average of KL distances are applied due to the reduction of noise power and local spectral variability. The performance of the novel statistical preprocessing algorithm has been compared with the sate-of-the-art in terms of RMSE reconstruction and average SAD errors on two real hyperspectral images known as HYDICE urban and AVIRIS Indian Pines in combination with several endmember extraction (EE) algorithms and its efficiency is evaluated. © 2021 IEEE.

关键词： Entropy