检索结果-内蒙古大学图书馆

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：

Scene Consistency Representation Learning for Video Scene Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Haoqian Chen, Keyu Luo, Yanan Qiao, Ruizhi Ren, Bo Liu, Haozhe Xie, Weicheng Shen, Linlin Computer Vision Institute Shenzhen University China Tencent YouTu Lab Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Key Laboratory of Intelligent Information Processing China KAUST Saudi Arabia

A long-term video, such as a movie or TV show, is composed of various scenes, each of which represents a series of shots sharing the same semantic story. Spotting the correct scene boundary from the long-term video is a challenging task, since a model must understand the storyline of the video to figure out where a scene starts and ends. To this end, we propose an effective Self-Supervised Learning (SSL) framework to learn better shot representations from unlabeled long-term videos. More specifically, we present an SSL scheme to achieve scene consistency, while exploring considerable data augmentation and shuffling methods to boost the model generalizability. Instead of explicitly learning the scene boundary features as in the previous methods, we introduce a vanilla temporal model with less inductive bias to verify the quality of the shot features. Our method achieves the state-of-the-art performance on the task of Video Scene Segmentation. Additionally, we suggest a more fair and reasonable benchmark to evaluate the performance of Video Scene Segmentation methods. The code is made available. © 2022, CC BY.

关键词： Semantics

UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Qiufu Jia, Xi Zhou, Jiancan Shen, Linlin Duan, Jinming National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Computer Vision Institute Shenzhen University China School of Computer Science University of Birmingham United Kingdom Aqara Lumi United Technology Co. Ltd China Alan Turing Institute United Kingdom SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require sophisticated pairing processes for training. Furthermore, neither method satisfies the requirements of real-world face verification applications, which expect a unified threshold separating positive from negative facial pairs. In this paper, we propose a unified threshold integrated sample-to-sample based loss (USS loss), which features an explicit unified threshold for distinguishing positive from negative pairs. Inspired by our USS loss, we also derive the sample-to-sample based softmax and BCE losses, and discuss their relationship. Extensive evaluation on multiple benchmark datasets, including MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace, demonstrates that the proposed USS loss is highly efficient and can work seamlessly with sample-to-class-based losses. The embedded loss (USS and sample-to-class Softmax loss) overcomes the pitfalls of previous approaches and the trained facial model UniTSFace exhibits exceptional performance, outperforming state-of-the-art methods, such as CosFace, ArcFace, VPL, AnchorFace, and UNPG. Our code is available at https://***/CVI-SZU/UniTSFace. © 2023, CC BY.

关键词： Face recognition

Deep Learning vs. Traditional 3d Registration: A Featureless 3d Registration Baseline

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Bojanic, David Bartol, Kristijan Forest, Josep Petkovic, Tomislav Pribanic, Tomislav University of Zagreb Faculty of Electrical Engineering and Computing Unska 3 Zagreb10000 Croatia TU Dresden Dresden01069 Germany University of Girona Computer Vision and Robotics Research Institute Plaça de Sant Domènec 3 Girona17004 Spain

Recent 3D registration methods are mostly learning-based that either find correspondences in feature space and match them, or directly estimate the registration transformation from the given point cloud features. Therefore, these feature based methods have difficulties with generalizing onto point clouds that differ substantially from their training data. We propose a simple featureless traditional 3D registration baseline method based on the weighted cross-correlation between two given point clouds. Our method achieves strong results on current benchmarking datasets, outperforming most deep-learning methods. We further propose a methodology to create a 3D registration benchmark, given a point cloud dataset, that provides a more informative evaluation of a method w.r.t. other benchmarks. We also propose to use the 3D registration parameter range of a benchmark as an indicator of its difficulty. Using this methodology, we create a novel FAUST-partial (FP) benchmark, based on the FAUST dataset, with several difficulty levels. The FP benchmark addresses the limitations of the current benchmarks: lack of data and parameter range variability, and allows to evaluate the strengths and weaknesses of a 3D registration method w.r.t. a single registration parameter. Using the new FP benchmark, we provide a thorough analysis of the current state-of-the-art methods. Our source code is available on GitHub. © 2023, The Authors. All rights reserved.

关键词： Deep learning

Constricting Normal Latent Space for Anomaly Detection with Normal-only Training Data

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Astrid, Marcella Zaheer, Muhammad Zaigham Lee, Seung-Ik Department of Artificial Intelligence University of Science and Technology Korea Republic of Field Robotics Research Section Electronics and Telecommunications Research Institute Korea Republic of Interdisciplinary Centre for Security Reliability and Trust University of Luxembourg Luxembourg Department of Computer Vision Mohamed Bin Zayed University of Artificial Intelligence United Arab Emirates

In order to devise an anomaly detection model using only normal training data, an autoencoder (AE) is typically trained to reconstruct the data. As a result, the AE can extract normal representations in its latent space. During test time, since AE is not trained using real anomalies, it is expected to poorly reconstruct the anomalous data. However, several researchers have observed that it is not the case. In this work, we propose to limit the reconstruction capability of AE by introducing a novel latent constriction loss, which is added to the existing reconstruction loss. By using our method, no extra computational cost is added to the AE during test time. Evaluations using three video anomaly detection benchmark datasets, i.e., Ped2, Avenue, and ShanghaiTech, demonstrate the effectiveness of our method in limiting the reconstruction capability of AE, which leads to a better anomaly detection model. © 2024, CC BY-NC-SA.

关键词： Anomaly detection

Inspecting Mega Solar Plants through computer vision and Drone Technologies

学校读者我要写书评

暂无评论

Inspecting Mega Solar Plants through Computer Vision and Dro...

Frontiers of Information Technology (FIT)

作者： Syed Umaid Ahmed Muhammad Affan Muhammad Ilyas Raza Muhammad Harris Hashmi Department of Computer Sciences National University of Computer and Emerging Sciences Karachi Pakistan SeaTech School of Engineering University of Toulon La Garde France Institute of Robotics and Computer Vision Innopolis University Innopolis Russia Department of Computer Science University of Alabama at Birmingham Birmingham United States

ISBN: (纸本)9798350345940

This research presents a unique approach for monitoring the large-scale grid-connected photovoltaic modules in solar power plants using state-of-art object detection YOLOv5 algorithm and classical image processing techniques. We have highlighted an integral part of the fully automated system in which a drone takes flight over the solar park and shoot the videos. Videos are preprocessed and used for trained YOLOv5 model to recognize the clean and dirty panels. The process is defined for a selected site and can be implemented using a Raspberry Pi. This system processes the images taken by drones, generates a report, and sends it to the concerned department automatically via email every day so that timely maintenance can be done for the long-life and safe operation of solar arrays. The inspection timeline for the same process was about one hundred and twenty hours, reduced to five minutes. It means that 99.93% of the time is saved through vision and robust automation techniques.

关键词： Photovoltaic systems computer vision Image processing Object detection Maintenance engineering Inspection Information technology

Risk Estimation for ICU Patients with Personalized Anomaly-Encoded Bedside Patient Data

学校读者我要写书评

暂无评论

Risk Estimation for ICU Patients with Personalized Anomaly-E...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Kai Wu Ee Heng Chen Felix Wirth Keti Vitanova Rüdiger Lange Darius Burschka German Heart Center Munich Munich Germany Department of Computer Engineering Machine Vision and Perception Group TUM School of Computation Information and Technology Technical University of Munich Garching Germany MIRMI - Munich Institute of Robotics and Machine Intelligence Technical University of Munich Munich

We propose a novel framework to estimate intensive care unit patients' health risk continuously with anomaly-encoded patient data. This framework consists of two modules. In the first module, we use Gaussian process models to learn change trend and day-night circulation in temporal patient data and annotate abnormal data. Such models provide dynamically adaptable bedside patient monitoring instead of conventional threshold-based monitoring. In the second module, we use the abnormal data together with the learned Gaussian models to estimate patients' risk level by predicting their in-hospital mortality and remaining length of stay in ICU ward. We show that prediction models with anomaly-encoded data have better performance than those with raw patient measurements, and they are comparable with state-of-art prediction models.

关键词：

DermoExpert: Skin lesion classification using a hybrid convolutional neural network through segmentation, transfer learning, and augmentation

学校读者我要写书评

暂无评论

Informatics in Medicine Unlocked 2022年 28卷

作者： Hasan, Md. Kamrul Elahi, Md. Toufick E. Alam, Md. Ashraful Jawad, Md. Tasnim Martí, Robert Department of Electrical and Electronic Engineering (EEE) Khulna University of Engineering & Technology (KUET) Khulna 9203 Bangladesh Computer Vision and Robotics Institute University of Girona Spain

Background and Objective: Although automated Skin Lesion Classification (SLC) is a crucial integral step in computer-aided diagnosis, it remains challenging due to variability in textures, colors, indistinguishable boundaries, and shapes. Methods: This article proposes an automated dermoscopic SLC framework named Dermoscopic Expert (DermoExpert). It combines the pre-processing and hybrid Convolutional Neural Network (hybrid-CNN). The proposed hybrid-CNN has three distinct feature extractor modules, which are fused to achieve better-depth feature maps of the lesion. Those single and fused feature maps are classified using different fully connected layers, then ensembled to predict a lesion class. In the proposed pre-processing, we apply lesion segmentation, augmentation (geometry- and intensity-based), and class rebalancing (penalizing the majority class's loss and merging additional images to the minority classes). Moreover, we leverage transfer learning from the pre-trained models. Finally, we deploy the weights of our DermoExpert to a possible web application. Results: We evaluate our DermoExpert on the ISIC-2016, ISIC-2017, and ISIC-2018 datasets, where the DermoExpert has achieved the area under the receiver operating characteristic curve (AUC) of 0.96, 0.95, and 0.97, respectively. The experimental results improve the state-of-the-art by the margins of 10.0% and 2.0%, respectively, for the ISIC-2016 and ISIC-2017 datasets in terms of AUC. The DermoExpert also outperforms by 3.0% for the ISIC-2018 dataset concerning a balanced accuracy. Conclusion: Since DermoExpert provides better classification outcomes on three different datasets, leading to a better recognition tool to assist dermatologists. Our source code and segmented masks for the ISIC-2018 dataset will be available as a public benchmark for future improvements. © 2022 The Authors

关键词： Convolutional neural networks Image augmentation ISIC skin lesion datasets Skin lesion classification and segmentation Transfer learning

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