检索结果-内蒙古大学图书馆

Deep Portrait Quality Assessment. A NTIRE 2024 Challenge Survey

学校读者我要写书评

暂无评论

Deep Portrait Quality Assessment. A NTIRE 2024 Challenge Sur...

IEEE computer Society Conference on computer vision and Pattern Recognition Workshops (CVPRW)

作者： Nicolas Chahine Marcos V. Conde Daniela Carfora Gabriel Pacianotto Benoit Pochon Sira Ferradans Radu Timofte Zhichao Duan Xinrui Xu Yipo Huang Quan Yuan Xiangfei Sheng Zhichao Yang Leida Li Haotian Fan Fangyuan Kong Yifang Xu Wei Sun Weixia Zhang Yanwei Jiang Haoning Wu Zicheng Zhang Jun Jia Yingjie Zhou Zhongpeng Ji Xiongkuo Min Weisi Lin Guangtao Zhai Xiaoqi Wang Junqi Liu Zixi Guo Yun Zhang Zewen Chen Wen Wang Juan Wang Bing Li DXOMARK CAIDAS & IFI Computer Vision Lab University of Würzburg Xidian University ByteDance Inc Shanghai Jiao Tong University Nanyang Technological University Huawei School of Electronics and Communication Engineering Sun Yat-sen University China State Key Laboratory of Multimodal Artificial Intelligence Systems CASIA School of Artificial Intelligence University of Chinese Academy of Sciences Beijing Jiaotong University

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

This paper reviews the NTIRE 2024 Portrait Quality Assessment Challenge, highlighting the proposed solutions and results. This challenge aims to obtain an efficient deep neural network capable of estimating the perceptual quality of real portrait photos. The methods must generalize to diverse scenes and diverse lighting conditions (indoor, outdoor, low-light), movement, blur, and other challenging conditions. In the challenge, 140 participants registered, and 35 submitted results during the challenge period. The performance of the top 5 submissions is reviewed and provided here as a gauge for the current state-of-the-art in Portrait Quality Assessment.

关键词： Surveys computer vision Reviews Conferences Lighting Artificial neural networks Quality assessment Pattern recognition

Object Detection, Recognition, Deep Learning, and the Universal Law of Generalization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Rustom, Faris B. Öğmen, Haluk Yazdanbakhsh, Arash Department of Psychological and Brain Sciences Computational Neuroscience and Vision Lab Center for Systems Neuroscience Boston University BostonMA United States Department of Electrical & Computer Engineering Laboratory of Perceptual and Cognitive Dynamics University of Denver DenverCO United States

Object detection and recognition are fundamental functions underlying the success of species. Because the appearance of an object exhibits a large variability, the brain has to group these different stimuli under the same object identity, a process of generalization. Does the process of generalization follow some general principles or is it an ad-hoc "bag-of-tricks"? The Universal Law of Generalization provided evidence that generalization follows similar properties across a variety of species and tasks. Here we test the hypothesis that the internal representations underlying generalization reflect the natural properties of object detection and recognition in our environment rather than the specifics of the system solving these problems. By training a deep-neural-network with images of "clear" and "camouflaged" animals, we found that, with a proper choice of category prototypes, the generalization functions are monotone decreasing, similar to the generalization functions of biological systems. Our findings support the hypothesis of the study. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

Fast Few-Shot Classification by Few-Iteration Meta-Learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tripathi, Ardhendu Shekhar Danelljan, Martin Van Gool, Luc Timofte, Radu The Computer Vision Lab Department of Electrical Engineering ETH Zurich Switzerland

Autonomous agents interacting with the real world need to learn new concepts efficiently and reliably. This requires learning in a low-data regime, which is a highly challenging problem. We address this task by introducing a fast optimization-based meta-learning method for few-shot classification. It consists of an embedding network, providing a general representation of the image, and a base learner module. The latter learns a linear classifier during the inference through an unrolled optimization procedure. We design an inner learning objective composed of (i) a robust classification loss on the support set and (ii) an entropy loss, allowing transductive learning from unlabeled query samples. By employing an efficient initialization module and a Steepest Descent based optimization algorithm, our base learner predicts a powerful classifier within only a few iterations. Further, our strategy enables important aspects of the base learner objective to be learned during meta-training. To the best of our knowledge, this work is the first to integrate both induction and transduction into the base learner in an optimization-based meta-learning framework. We perform a comprehensive experimental analysis, demonstrating the speed and effectiveness of our approach on four few-shot classification datasets. The Code is available at https://***/4rdhendu/FIML. Copyright © 2020, The Authors. All rights reserved.

关键词： Optimization

Application of an enhanced deep super-resolution network in retinal image analysis 30

学校读者我要写书评

暂无评论

Application of an enhanced deep super-resolution network in ...

30th Conference on Ophthalmic Technologies

作者： Gulati, Tanmay Sengupta, Sourya Lakshminarayanan, Vasudevan Department of Computer Science and Engineering Manipal Institute of Technology Manipal India Theoretical and Experimental Epistemology Lab School of Optometry and Vision Science University of Waterloo ON Canada Department of Systems Design Engineering University of Waterloo ON Canada

ISBN: (纸本)9781510631991

Fundus imaging is widely used for the diagnosis of retinal diseases. Major ophthalmic diseases like glaucoma, diabetic retinopathy (DR), age-related macular degeneration (AMD) are diagnosed by examining retinal fundus images. Therefore, the efficient and reliable diagnosis largely depends upon the resolution of the images. In different diseased conditions, different pathologies and landmarks (haemorrhages, microaneurysms, exudates, blood vessels, optic disc and optic cup, fovea) of the retina get affected. In clinical situations it is often not possible to obtain good high-resolution images. Here, the techniques of super-resolution can be applied. The objective of super-resolution is to obtain a high-resolution image from a low-resolution input image. In this paper, we present results of the application of enhanced deep residual networks for single image super-resolution (EDSR) on retinal fundus images. This network is based on the SRResNet architecture involving skip connections. Using the public RIGA dataset, which consists of glaucoma and normal fundus images, we have trained the model using 2x, 4x and 8x scaling with three different optimizers each (namely ADAM, Stochastic Gradient Descent and RMSprop) to determine which optimizer is best for the different scales. We have also provided results obtained by varying the residual blocks in the network. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Diagnosis

SynFacePAD 2023: Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Fang, Meiling Huber, Marco Fierrez, Julian Ramachandra, Raghavendra Damer, Naser Alkhaddour, Alhasan Kasantcev, Maksim Pryadchenko, Vasiliy Yang, Ziyuan Huangfu, Huijie Chen, Yingyu Zhang, Yi Pan, Yuchen Jiang, Junjun Liu, Xianming Sun, Xianyun Wang, Caiyong Liu, Xingyu Chang, Zhaohua Zhao, Guangzhe Tapia, Juan Gonzalez-Soler, Lazaro Aravena, Carlos Schulz, Daniel Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science TU Darmstadt Darmstadt Germany Biometrics and Data Pattern Analytics Lab Universidad Autonoma de Madrid Spain Norway ID R&D Inc. New York United States School of Cyber Science and Engineering Sichuan University Chengdu China School of Computer Science and Technology Harbin Institute of Technology Harbin China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture China Biometrics and Security Research Group Hochschule Darmstadt Darmstadt Germany I+D Vision Center Santiago Chile

This paper presents a summary of the Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data (SynFacePAD 2023) held at the 2023 International Joint Conference on Biometrics (IJCB 2023). The competition attracted a total of 8 participating teams with valid submissions from academia and industry. The competition aimed to motivate and attract solutions that target detecting face presentation attacks while considering synthetic-based training data motivated by privacy, legal and ethical concerns associated with personal data. To achieve that, the training data used by the participants was limited to synthetic data provided by the organizers. The submitted solutions presented innovations and novel approaches that led to outperforming the considered baseline in the investigated benchmarks. © 2023, CC BY-NC-SA.

关键词： Competition

Terahertz compressive imaging: understanding and improvement by a better strategy for data selection

学校读者我要写书评

暂无评论

Terahertz compressive imaging: understanding and improvement...

作者： Xing, Chungui Qi, Feng Liu, Zhaoyang Wang, Yelong Guo, Shuxu State Key Laboratory on Integrated Optoelectronics College of Electronic Science and Engineering Jilin University Changchun China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang China Key Lab of Image Understanding and Computer Vision Shenyang China

Compressive sensing (CS) is a novel sampling modality, which indicates the signals can be sampled at a rate much below the Nyquist sampling rate. CS has increasing interest recently due to high demand of rapid, efficient, and in-expensive signal processing applications in the μmWave and mmWave frequencies, such as communication and imaging. There have been a lot of theoretical studies on this topic, but there is a lack of systematic experimental analysis of the implementation method itself. In this paper, we have investigated the influencing factors of terahertz compressive sensing based on experimental results, including illumination and the size of the pixel. Besides, to differentiate from current approaches, which generally make full use of the data, we propose to sort the data first and select a part of them based on amplitude, which might deliver a better image by prompting the mathematical calculations compulsively. We believe that such considerations given above would help to make a better system design and improve the performance of compressive imaging, and these results will also be helpful in the application of terahertz communication. © 2021 John Wiley & Sons, Ltd

关键词： Compressed sensing

GeneSegNet: a deep learning framework for cell segmentation by integrating gene expression and imaging

学校读者我要写书评

暂无评论

Genome Biology 2023年第1期24卷 235-235页

作者： Wang, Yuxing Wang, Wenguan Liu, Dongfang Hou, Wenpin Zhou, Tianfei Ji, Zhicheng Department of Computer Engineering Rochester Institute of Technology Rochester United States Department of Biostatistics and Bioinformatics Duke University School of Medicine Durham United States The ReLER Lab from the Australian Artificial Intelligence Institute (AAII) University of Technology Sydney Sydney Australia Department of Biostatistics Columbia University Mailman School of Public Health New York City United States Computer Vision Lab ETH Zurich Zurich Switzerland

When analyzing data from in situ RNA detection technologies, cell segmentation is an essential step in identifying cell boundaries, assigning RNA reads to cells, and studying the gene expression and morphological features of cells. We developed a deep-learning-based method, GeneSegNet, that integrates both gene expression and imaging information to perform cell segmentation. GeneSegNet also employs a recursive training strategy to deal with noisy training labels. We show that GeneSegNet significantly improves cell segmentation performances over existing methods that either ignore gene expression information or underutilize imaging information. © 2023, BioMed Central Ltd., part of Springer Nature.

关键词： Cell segmentation Deep learning In situ hybridization Spatial transcriptomics

NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Carrion Ojeda, Dustin Javier Chen, Hong El Baz, Adrian Escalera, Sergio Guan, Chaoyu Guyon, Isabelle Ullah, Ihsan Wang, Xin Zhu, Wenwu LISN CNRS INRIA Université Paris-Saclay France Department of Computer Science and Technology Tsinghua University China MILA - Québec AI Institute Montréal Canada NeuroPoly Lab Institute of Biomedical Engineering Polytechnique Montréal Canada ChaLearn United States Computer Vision Center Universitat de Barcelona Spain

We present the design and baseline results for a new challenge in the ChaLearn meta-learning series, accepted at NeurIPS’22, focusing on "cross-domain" meta-learning. Meta-learning aims to leverage experience gained from previous tasks to solve new tasks efficiently (i.e., with better performance, little training data, and/or modest computational resources). While previous challenges in the series focused on within-domain few-shot learning problems, with the aim of learning efficiently N-way k-shot tasks (i.e., N class classification problems with k training examples), this competition challenges the participants to solve "any-way" and "any-shot" problems drawn from various domains (healthcare, ecology, biology, manufacturing, and others), chosen for their humanitarian and societal impact. To that end, we created Meta-Album, a meta-dataset of 40 image classification datasets from 10 domains, from which we carve out tasks with any number of "ways" (within the range 2-20) and any number of "shots" (within the range 1-20). The competition is with code submission, fully blind-tested on the Codalab challenge platform. The code of the winners will be open-sourced, enabling the deployment of automated machine learning solutions for few-shot image classification across several domains. Copyright © 2022, The Authors. All rights reserved.

关键词： Image classification

Customizable Avatars with Dynamic Facial Action Coded Expressions (CADyFACE) for Improved User Engagement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Witherow, Megan A. Butler, Crystal Shields, Winston J. Ilgin, Furkan Diawara, Norou Keener, Janice Harrington, John W. Iftekharuddin, Khan M. The Vision Lab Department of Electrical & Computer Engineering Old Dominion University NorfolkVA23529 United States FACS Coder Ellicott CityMD21043 United States The Department of Mathematics & Statistics Old Dominion University NorfolkVA23529 United States The Department of Pediatrics Eastern Virginia Medical School Children’s Hospital of The King’s Daughters NorfolkVA23507 United States

Customizable 3D avatar-based facial expression stimuli may improve user engagement in behavioral biomarker discovery and therapeutic intervention for autism, Alzheimer’s disease, facial palsy, and more. However, there is a lack of customizable avatar-based stimuli with Facial Action Coding System (FACS) action unit (AU) labels. Therefore, this study focuses on (1) FACS-labeled, customizable avatar-based expression stimuli for maintaining subjects’ engagement, (2) learning-based measurements that quantify subjects’ facial responses to such stimuli, and (3) validation of constructs represented by stimulus-measurement pairs. We propose Customizable Avatars with Dynamic Facial Action Coded Expressions (CADyFACE) labeled with AUs by a certified FACS expert. To measure subjects’ AUs in response to CADyFACE, we propose a novel Beta-guided Correlation and Multi-task Expression learning neural network (BeCoME-Net) for multi-label AU detection. The beta-guided correlation loss encourages feature correlation with AUs while discouraging correlation with subject identities for improved generalization. We train BeCoME-Net for unilateral and bilateral AU detection and compare with state-of-the-art approaches. To assess construct validity of CADyFACE and BeCoME-Net, twenty healthy adult volunteers complete expression recognition and mimicry tasks in an online feasibility study while webcam-based eye-tracking and video are collected. We test validity of multiple constructs, including face preference during recognition and AUs during mimicry. Copyright © 2024, The Authors. All rights reserved.

关键词： Eye tracking