检索结果-内蒙古大学图书馆

Spin-UP: Spin Light for Natural Light Uncalibrated Photometric Stereo

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Zongrui Lu, Zhan Yan, Haojie Shi, Boxin Pan, Gang Zheng, Qian Jiang, Xudong Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore College of Computer Science and Technology Zhejiang University China The State Key Lab of Brain-Machine Intelligence Zhejiang University China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China

Natural Light Uncalibrated Photometric Stereo (NaUPS) relieves the strict environment and light assumptions in classical Uncalibrated Photometric Stereo (UPS) methods. However, due to the intrinsic ill-posedness and high-dimensional ambiguities, addressing NaUPS is still an open question. Existing works impose strong assumptions on the environment lights and objects' material, restricting the effectiveness in more general scenarios. Alternatively, some methods leverage supervised learning with intricate models while lacking interpretability, resulting in a biased estimation. In this work, we propose Spin Light Uncalibrated Photometric Stereo (Spin-UP), an unsupervised method to tackle NaUPS in various environment lights and objects. The proposed method uses a novel setup that captures the object's images on a rotatable platform, which mitigates NaUPS's ill-posedness by reducing unknowns and provides reliable priors to alleviate NaUPS's ambiguities. Leveraging neural inverse rendering and the proposed training strategies, Spin-UP recovers surface normals, environment light, and isotropic reflectance under complex natural light with low computational cost. Experiments have shown that Spin-UP outperforms other supervised/unsupervised NaUPS methods and achieves state-of-the-art performance on synthetic and real-world datasets. Codes and data are available at https://***/LMozart/CVPR2024-SpinUP. Copyright © 2024, The Authors. All rights reserved.

关键词： Photometry

Pathformer3D: A 3D Scanpath Transformer for 360° Images

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Quan, Rong Lai, Yantao Qiu, Mengyu Liang, Dong College of Artificial Intelligence Nanjing University of Aeronautics and Astronautics The Key Laboratory of Brain-Machine Intelligence Technology Ministry of Education Nanjing211106 China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Shenzhen Research Institute Nanjing University of Aeronautics and Astronautics Shenzhen China

Scanpath prediction in 360° images can help realize rapid rendering and better user interaction in Virtual/Augmented Reality applications. However, existing scanpath prediction models for 360° images execute scanpath prediction on 2D equirectangular projection plane, which always result in big computation error owing to the 2D plane’s distortion and coordinate discontinuity. In this work, we perform scanpath prediction for 360° images in 3D spherical coordinate system and proposed a novel 3D scanpath Transformer named Pathformer3D. Specifically, a 3D Transformer encoder is first used to extract 3D contextual feature representation for the 360° image. Then, the contextual feature representation and historical fixation information are input into a Transformer decoder to output current time step’s fixation embedding, where the self-attention module is used to imitate the visual working memory mechanism of human visual system and directly model the time dependencies among the fixations. Finally, a 3D Gaussian distribution is learned from each fixation embedding, from which the fixation position can be sampled. Evaluation on four panoramic eye-tracking datasets demonstrates that Pathformer3D outperforms the current state-of-the-art methods. Code is available at https://***/lsztzp/ Pathformer3D. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

NeuroSparse: An Unsupervised Framework for Inferring brain Connectivity in Autism Diagnosis

学校读者我要写书评

暂无评论

NeuroSparse: An Unsupervised Framework for Inferring Brain C...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Shuqi Yang Lijuan Zhang Qing Lan Qiujie Ma Huan Huang Jiaqing Miao Shiyu Mou Cheng Luo Dezhong Yao Ying Tan The Key Laboratory for Computer Systems of State Ethnic Affairs Commission Southwest Minzu University Chengdu China The Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation University of Electronic Science and Technology of China Chengdu China Department of Biomedical Engineering Faculty of Engineering University of Malaya Kuala Lumpur Malaysia

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Autism spectrum disorder (ASD) is a mental disorder that severely affects social interaction and communication skills. A timely and accurate diagnosis is crucial for effective intervention. However, as an objective diagnostic tool, the existence of spurious connections and noise within the functional connectivity (FC) matrix in the brain contribute to the complexity of ASD diagnosis. In this study, we propose an unsupervised sparse graph structure learning framework, called NeuroSparse, for reasoning regarding the topological connectivity relationships between brain regions. First, the framework fuses spatiotemporal information from static and dynamic FC to provide a comprehensive representation of complex brain networks. Next, the context and neighborhood information of nodes are captured as their local and global embeddings, and the latent representations of node embeddings are learned, which are then decoded to infer the connectivity relationships among the regions of interest. Finally, we introduce three innovative loss functions to regularize and optimize the sparse representation generation process. The experimental results showed that, after learning using NeuroSparse, the FC matrix achieved state-of-the-art performance in ASD diagnosis using only a simple multilayer perceptron, indicating its wide-ranging application potential. The code is available at https://***/yangshuqigit/NeuroSparse.

关键词： Autism Visualization Sparse approximation Mental disorders Noise Predictive models Multilayer perceptrons brain modeling Spatiotemporal phenomena Sparse matrices

Multi-view laplacian eigenmaps based on bag-of-neighbors for RGBD human emotion recognition

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Shenglan Guo, Shuai Qiao, Hong Wang, Yang Wang, Bin Luo, Wenbo Zhang, Mingming Zhang, keye Du, Bixuan School of Computer Science and Technology Dalian University of Technology Dalian116024 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Research Center for Brain and Cognitive Neuroscience Liaoning Normal University Dalian116024 China

Human emotion recognition is an important direction in the field of biometric and information forensics. However, most existing human emotion research are based on the single RGB view. In this paper, we introduce a RGBD video-emotion dataset and a RGBD face-emotion dataset for research. To our best knowledge, this may be the first RGBD video-emotion dataset. We propose a new supervised nonlinear multi-view laplacian eigenmaps (MvLE) approach and a multihidden-layer out-of-sample network (MHON) for RGB-D human emotion recognition. To get better representations of RGB view and depth view, MvLE is used to map the training set of both views from original space into the common subspace. As RGB view and depth view lie in different spaces, a new distance metric bag of neighbors (BON) used in MvLE can get the similar distributions of the two views. Finally, MHON is used to get the low-dimensional representations of test data and predict their labels. MvLE can deal with the cases that RGB view and depth view have different size of features, even different number of samples and classes. And our methods can be easily extended to more than two views. The experiment results indicate the effectiveness of our methods over some state-of-art methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Laplace transforms

Optimizing interconnections to maximize the spectral radius of interdependent networks

学校读者我要写书评

暂无评论

Physical Review E 2017年第3期95卷 032308-032308页

作者： Huashan Chen Xiuyan Zhao Feng Liu Shouhuai Xu Wenlian Lu State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing 100093 China School of Mathematical Sciences Fudan University Shanghai 200433 People's Republic of China Department of Computer Science University of Texas at San Antonio San Antonio Texas 78249 USA Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai 200433 China

The spectral radius (i.e., the largest eigenvalue) of the adjacency matrices of complex networks is an important quantity that governs the behavior of many dynamic processes on the networks, such as synchronization and epidemics. Studies in the literature focused on bounding this quantity. In this paper, we investigate how to maximize the spectral radius of interdependent networks by optimally linking k internetwork connections (or interconnections for short). We derive formulas for the estimation of the spectral radius of interdependent networks and employ these results to develop a suite of algorithms that are applicable to different parameter regimes. In particular, a simple algorithm is to link the k nodes with the largest k eigenvector centralities in one network to the node in the other network with a certain property related to both networks. We demonstrate the applicability of our algorithms via extensive simulations. We discuss the physical implications of the results, including how the optimal interconnections can more effectively decrease the threshold of epidemic spreading in the susceptible-infected-susceptible model and the threshold of synchronization of coupled Kuramoto oscillators.

关键词： Network optimization

Adversarial Texture for Fooling Person Detectors in the Physical World

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Zhanhao Huang, Siyuan Zhu, Xiaopei Sun, Fuchun Zhang, Bo Hu, Xiaolin Department of Computer Science and Technology Institute for Artificial Intelligence State Key Laboratory of Intelligent Technology and Systems BNRist Tsinghua University Beijing China School of Integrated Circuits Tsinghua University Beijing China IDG/McGovern Institute for Brain Research Tsinghua University Beijing China Beijing China

Nowadays, cameras equipped with AI systems can capture and analyze images to detect people automatically. However, the AI system can make mistakes when receiving deliberately designed patterns in the real world, i.e., physical adversarial examples. Prior works have shown that it is possible to print adversarial patches on clothes to evade DNN-based person detectors. However, these adversarial examples could have catastrophic drops in the attack success rate when the viewing angle (i.e., the camera's angle towards the object) changes. To perform a multi-angle attack, we propose Adversarial Texture (AdvTexture). AdvTexture can cover clothes with arbitrary shapes so that people wearing such clothes can hide from person detectors from different viewing angles. We propose a generative method, named Toroidal-Cropping-based Expandable Generative Attack (TC-EGA), to craft AdvTexture with repetitive structures. We printed several pieces of cloth with AdvTexure and then made T-shirts, skirts, and dresses in the physical world. Experiments showed that these clothes could fool person detectors in the physical world. Copyright © 2022, The Authors. All rights reserved.

关键词： Textures

Infrared Invisible Clothing: Hiding from Infrared Detectors at Multiple Angles in Real World

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhu, Xiaopei Hu, Zhanhao Huang, Siyuan Li, Jianmin Hu, Xiaolin School of Integrated Circuits Tsinghua University Beijing China Department of Computer Science and Technology Institute for Artificial Intelligence State Key Laboratory of Intelligent Technology and Systems BNRist Tsinghua University Beijing China IDG/McGovern Institute for Brain Research Tsinghua University Beijing China Beijing China

Thermal infrared imaging is widely used in body temperature measurement, security monitoring, and so on, but its safety research attracted attention only in recent years. We proposed the infrared adversarial clothing, which could fool infrared pedestrian detectors at different angles. We simulated the process from cloth to clothing in the digital world and then designed the adversarial "QR code" pattern. The core of our method is to design a basic pattern that can be expanded periodically, and make the pattern after random cropping and deformation still have an adversarial effect, then we can process the flat cloth with an adversarial pattern into any 3D clothes. The results showed that the optimized "QR code" pattern lowered the Average Precision (AP) of YOLOv3 by 87.7%, while the random "QR code" pattern and blank pattern lowered the AP of YOLOv3 by 57.9% and 30.1%, respectively, in the digital world. We then manufactured an adversarial shirt with a new material: aerogel. Physical-world experiments showed that the adversarial "QR code" pattern clothing lowered the AP of YOLOv3 by 64.6%, while the random "QR code" pattern clothing and fully heat-insulated clothing lowered the AP of YOLOv3 by 28.3% and 22.8%, respectively. We used the model ensemble technique to improve the attack transferability to unseen models. Copyright © 2022, The Authors. All rights reserved.

关键词： Thermography (imaging)

Pyramid Pixel Context Adaption Network for Medical Image Classification with Supervised Contrastive Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Xiaoqing Xiao, Zunjie Wu, Xiao Chen, Yanlin Zhao, Jilu Hu, Yan Liu, Jiang Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Center for High Performance Computing Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen518055 China Singapore Eye Research Institute 169856 Singapore

Spatial attention mechanism has been widely incorporated into deep neural networks (DNNs), significantly lifting the performance in computer vision tasks via long-range dependency modeling. However, it may perform poorly in medical image analysis. Unfortunately, existing efforts are often unaware that long-range dependency modeling has limitations in highlighting subtle lesion regions. To overcome this limitation, we propose a practical yet lightweight architectural unit, Pyramid Pixel Context Adaption (PPCA) module, which exploits multiscale pixel context information to recalibrate pixel position in a pixel-independent manner dynamically. PPCA first applies a well-designed cross-channel pyramid pooling to aggregate multiscale pixel context information, then eliminates the inconsistency among them by the well-designed pixel normalization, and finally estimates per pixel attention weight via a pixel context integration. By embedding PPCA into a DNN with negligible overhead, the PPCANet is developed for medical image classification. In addition, we introduce supervised contrastive learning to enhance feature representation by exploiting the potential of label information via supervised contrastive loss. The extensive experiments on six medical image datasets show that PPCANet outperforms state-of-the-art attention-based networks and recent deep neural networks. We also provide visual analysis and ablation study to explain the behavior of PPCANet in the decision-making process. © 2023, CC BY.

关键词： Pixels

Mitigating Unfairness via Evolutionary Multi-objective Ensemble Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Qingquan Liu, Jialin Zhang, Zeqi Wen, Junyi Mao, Bifei Yao, Xin The Research Institute of Trustworthy Autonomous System Southern University of Science and Technology Shenzhen518055 China The Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The Trustworthiness Theory Research Center Huawei Technologies Co. Ltd. Shenzhen518129 China The School of Computer Science University of Birmingham United Kingdom

In the literature of mitigating unfairness in machine learning, many fairness measures are designed to evaluate predictions of learning models and also utilised to guide the training of fair models. It has been theoretically and empirically shown that there exist conflicts and inconsistencies among accuracy and multiple fairness measures. Optimising one or several fairness measures may sacrifice or deteriorate other measures. Two key questions should be considered, how to simultaneously optimise accuracy and multiple fairness measures, and how to optimise all the considered fairness measures more effectively. In this paper, we view the mitigating unfairness problem as a multi-objective learning problem considering the conflicts among fairness measures. A multi-objective evolutionary learning framework is used to simultaneously optimise several metrics (including accuracy and multiple fairness measures) of machine learning models. Then, ensembles are constructed based on the learning models in order to automatically balance different metrics. Empirical results on eight well-known datasets demonstrate that compared with the state-of-the-art approaches for mitigating unfairness, our proposed algorithm can provide decision-makers with better tradeoffs among accuracy and multiple fairness metrics. Furthermore, the high-quality models generated by the framework can be used to construct an ensemble to automatically achieve a better tradeoff among all the considered fairness metrics than other ensemble methods. Our code is publicly available at https://***/qingquan63/FairEMOL. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning